Hugging Face's logo

LiquidAI
/
LFM2.5-2.6B-MLX

Text Generation
MLX
Safetensors
liquid
lfm2.5
edge
Model card Files
xet
 Community
mlabonne ykhrustalev commited on
Commit
58e239c
·
0 Parent(s):

Initial commit

Browse files

Co-authored-by: ykhrustalev <ykhrustalev@users.noreply.huggingface.co>

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +43 -0
  2. 4bit/chat_template.jinja +125 -0
  3. 4bit/config.json +97 -0
  4. 4bit/generation_config.json +15 -0
  5. 4bit/model.safetensors +3 -0
  6. 4bit/model.safetensors.index.json +608 -0
  7. 4bit/tokenizer.json +3 -0
  8. 4bit/tokenizer_config.json +13 -0
  9. 5bit/chat_template.jinja +125 -0
  10. 5bit/config.json +97 -0
  11. 5bit/generation_config.json +15 -0
  12. 5bit/model.safetensors +3 -0
  13. 5bit/model.safetensors.index.json +608 -0
  14. 5bit/tokenizer.json +3 -0
  15. 5bit/tokenizer_config.json +13 -0
  16. 6bit/chat_template.jinja +125 -0
  17. 6bit/config.json +87 -0
  18. 6bit/generation_config.json +15 -0
  19. 6bit/model.safetensors +3 -0
  20. 6bit/model.safetensors.index.json +608 -0
  21. 6bit/tokenizer.json +3 -0
  22. 6bit/tokenizer_config.json +13 -0
  23. 8bit/chat_template.jinja +125 -0
  24. 8bit/config.json +87 -0
  25. 8bit/generation_config.json +15 -0
  26. 8bit/model.safetensors +3 -0
  27. 8bit/model.safetensors.index.json +608 -0
  28. 8bit/tokenizer.json +3 -0
  29. 8bit/tokenizer_config.json +13 -0
  30. LICENSE +71 -0
  31. README.md +89 -0
  32. bf16/chat_template.jinja +125 -0
  33. bf16/config.json +77 -0
  34. bf16/generation_config.json +15 -0
  35. bf16/model-00001-of-00002.safetensors +3 -0
  36. bf16/model-00002-of-00002.safetensors +3 -0
  37. bf16/model.safetensors.index.json +274 -0
  38. bf16/tokenizer.json +3 -0
  39. bf16/tokenizer_config.json +13 -0
  40. mxfp4/chat_template.jinja +125 -0
  41. mxfp4/config.json +97 -0
  42. mxfp4/generation_config.json +15 -0
  43. mxfp4/model.safetensors +3 -0
  44. mxfp4/model.safetensors.index.json +441 -0
  45. mxfp4/tokenizer.json +3 -0
  46. mxfp4/tokenizer_config.json +13 -0
  47. mxfp8/chat_template.jinja +125 -0
  48. mxfp8/config.json +87 -0
  49. mxfp8/generation_config.json +15 -0
  50. mxfp8/model.safetensors +3 -0
.gitattributes ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ bf16/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ 8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ 6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ 5bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ 4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ mxfp8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ mxfp4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ nvfp4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
4bit/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
4bit/config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 64,
69
+ "bits": 4,
70
+ "mode": "affine",
71
+ "model.embed_tokens": {
72
+ "group_size": 64,
73
+ "bits": 6,
74
+ "mode": "affine"
75
+ }
76
+ },
77
+ "quantization_config": {
78
+ "group_size": 64,
79
+ "bits": 4,
80
+ "mode": "affine",
81
+ "model.embed_tokens": {
82
+ "group_size": 64,
83
+ "bits": 6,
84
+ "mode": "affine"
85
+ }
86
+ },
87
+ "rope_parameters": {
88
+ "rope_theta": 10000000.0,
89
+ "rope_type": "default"
90
+ },
91
+ "rope_theta": 10000000.0,
92
+ "tie_word_embeddings": true,
93
+ "transformers_version": "5.2.0",
94
+ "use_cache": true,
95
+ "use_pos_enc": true,
96
+ "vocab_size": 128000
97
+ }
4bit/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
4bit/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef350b75815752f8bff8c064c9fc8bd8b5709577d72943436852013d2bcd4691
3
+ size 1583152892
4bit/model.safetensors.index.json ADDED
@@ -0,0 +1,608 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1583085568,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.embedding_norm.weight": "model.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
18
+ "model.layers.0.feed_forward.w1.biases": "model.safetensors",
19
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.0.feed_forward.w2.biases": "model.safetensors",
22
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
23
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
24
+ "model.layers.0.feed_forward.w3.biases": "model.safetensors",
25
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
26
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.1.feed_forward.w1.biases": "model.safetensors",
37
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
38
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
39
+ "model.layers.1.feed_forward.w2.biases": "model.safetensors",
40
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
41
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
42
+ "model.layers.1.feed_forward.w3.biases": "model.safetensors",
43
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
44
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model.safetensors",
47
+ "model.layers.10.conv.conv.weight": "model.safetensors",
48
+ "model.layers.10.conv.in_proj.biases": "model.safetensors",
49
+ "model.layers.10.conv.in_proj.scales": "model.safetensors",
50
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
51
+ "model.layers.10.conv.out_proj.biases": "model.safetensors",
52
+ "model.layers.10.conv.out_proj.scales": "model.safetensors",
53
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
54
+ "model.layers.10.feed_forward.w1.biases": "model.safetensors",
55
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
56
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
57
+ "model.layers.10.feed_forward.w2.biases": "model.safetensors",
58
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
59
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
60
+ "model.layers.10.feed_forward.w3.biases": "model.safetensors",
61
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
62
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
63
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
64
+ "model.layers.10.operator_norm.weight": "model.safetensors",
65
+ "model.layers.11.conv.conv.weight": "model.safetensors",
66
+ "model.layers.11.conv.in_proj.biases": "model.safetensors",
67
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
68
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
69
+ "model.layers.11.conv.out_proj.biases": "model.safetensors",
70
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
71
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
72
+ "model.layers.11.feed_forward.w1.biases": "model.safetensors",
73
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
74
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
75
+ "model.layers.11.feed_forward.w2.biases": "model.safetensors",
76
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
77
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
78
+ "model.layers.11.feed_forward.w3.biases": "model.safetensors",
79
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
80
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
81
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
82
+ "model.layers.11.operator_norm.weight": "model.safetensors",
83
+ "model.layers.12.conv.conv.weight": "model.safetensors",
84
+ "model.layers.12.conv.in_proj.biases": "model.safetensors",
85
+ "model.layers.12.conv.in_proj.scales": "model.safetensors",
86
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
87
+ "model.layers.12.conv.out_proj.biases": "model.safetensors",
88
+ "model.layers.12.conv.out_proj.scales": "model.safetensors",
89
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
90
+ "model.layers.12.feed_forward.w1.biases": "model.safetensors",
91
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
92
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
93
+ "model.layers.12.feed_forward.w2.biases": "model.safetensors",
94
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
95
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
96
+ "model.layers.12.feed_forward.w3.biases": "model.safetensors",
97
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
98
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
99
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
100
+ "model.layers.12.operator_norm.weight": "model.safetensors",
101
+ "model.layers.13.feed_forward.w1.biases": "model.safetensors",
102
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
103
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
104
+ "model.layers.13.feed_forward.w2.biases": "model.safetensors",
105
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
106
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
107
+ "model.layers.13.feed_forward.w3.biases": "model.safetensors",
108
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
109
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
110
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
111
+ "model.layers.13.operator_norm.weight": "model.safetensors",
112
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
113
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
114
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
115
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
116
+ "model.layers.13.self_attn.out_proj.biases": "model.safetensors",
117
+ "model.layers.13.self_attn.out_proj.scales": "model.safetensors",
118
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
119
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
120
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
121
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
122
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
124
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
125
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
126
+ "model.layers.14.conv.conv.weight": "model.safetensors",
127
+ "model.layers.14.conv.in_proj.biases": "model.safetensors",
128
+ "model.layers.14.conv.in_proj.scales": "model.safetensors",
129
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
130
+ "model.layers.14.conv.out_proj.biases": "model.safetensors",
131
+ "model.layers.14.conv.out_proj.scales": "model.safetensors",
132
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
133
+ "model.layers.14.feed_forward.w1.biases": "model.safetensors",
134
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
135
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
136
+ "model.layers.14.feed_forward.w2.biases": "model.safetensors",
137
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
138
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
139
+ "model.layers.14.feed_forward.w3.biases": "model.safetensors",
140
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
141
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
142
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
143
+ "model.layers.14.operator_norm.weight": "model.safetensors",
144
+ "model.layers.15.conv.conv.weight": "model.safetensors",
145
+ "model.layers.15.conv.in_proj.biases": "model.safetensors",
146
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
147
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
148
+ "model.layers.15.conv.out_proj.biases": "model.safetensors",
149
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
150
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
151
+ "model.layers.15.feed_forward.w1.biases": "model.safetensors",
152
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
153
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
154
+ "model.layers.15.feed_forward.w2.biases": "model.safetensors",
155
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
156
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
157
+ "model.layers.15.feed_forward.w3.biases": "model.safetensors",
158
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
159
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
160
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
161
+ "model.layers.15.operator_norm.weight": "model.safetensors",
162
+ "model.layers.16.conv.conv.weight": "model.safetensors",
163
+ "model.layers.16.conv.in_proj.biases": "model.safetensors",
164
+ "model.layers.16.conv.in_proj.scales": "model.safetensors",
165
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
166
+ "model.layers.16.conv.out_proj.biases": "model.safetensors",
167
+ "model.layers.16.conv.out_proj.scales": "model.safetensors",
168
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
169
+ "model.layers.16.feed_forward.w1.biases": "model.safetensors",
170
+ "model.layers.16.feed_forward.w1.scales": "model.safetensors",
171
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
172
+ "model.layers.16.feed_forward.w2.biases": "model.safetensors",
173
+ "model.layers.16.feed_forward.w2.scales": "model.safetensors",
174
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
175
+ "model.layers.16.feed_forward.w3.biases": "model.safetensors",
176
+ "model.layers.16.feed_forward.w3.scales": "model.safetensors",
177
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
178
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
179
+ "model.layers.16.operator_norm.weight": "model.safetensors",
180
+ "model.layers.17.feed_forward.w1.biases": "model.safetensors",
181
+ "model.layers.17.feed_forward.w1.scales": "model.safetensors",
182
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
183
+ "model.layers.17.feed_forward.w2.biases": "model.safetensors",
184
+ "model.layers.17.feed_forward.w2.scales": "model.safetensors",
185
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
186
+ "model.layers.17.feed_forward.w3.biases": "model.safetensors",
187
+ "model.layers.17.feed_forward.w3.scales": "model.safetensors",
188
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
189
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
190
+ "model.layers.17.operator_norm.weight": "model.safetensors",
191
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
192
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
193
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
194
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
195
+ "model.layers.17.self_attn.out_proj.biases": "model.safetensors",
196
+ "model.layers.17.self_attn.out_proj.scales": "model.safetensors",
197
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
198
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
199
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
200
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
201
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
202
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
203
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
204
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
205
+ "model.layers.18.conv.conv.weight": "model.safetensors",
206
+ "model.layers.18.conv.in_proj.biases": "model.safetensors",
207
+ "model.layers.18.conv.in_proj.scales": "model.safetensors",
208
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
209
+ "model.layers.18.conv.out_proj.biases": "model.safetensors",
210
+ "model.layers.18.conv.out_proj.scales": "model.safetensors",
211
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
212
+ "model.layers.18.feed_forward.w1.biases": "model.safetensors",
213
+ "model.layers.18.feed_forward.w1.scales": "model.safetensors",
214
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
215
+ "model.layers.18.feed_forward.w2.biases": "model.safetensors",
216
+ "model.layers.18.feed_forward.w2.scales": "model.safetensors",
217
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
218
+ "model.layers.18.feed_forward.w3.biases": "model.safetensors",
219
+ "model.layers.18.feed_forward.w3.scales": "model.safetensors",
220
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
221
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
222
+ "model.layers.18.operator_norm.weight": "model.safetensors",
223
+ "model.layers.19.conv.conv.weight": "model.safetensors",
224
+ "model.layers.19.conv.in_proj.biases": "model.safetensors",
225
+ "model.layers.19.conv.in_proj.scales": "model.safetensors",
226
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
227
+ "model.layers.19.conv.out_proj.biases": "model.safetensors",
228
+ "model.layers.19.conv.out_proj.scales": "model.safetensors",
229
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
230
+ "model.layers.19.feed_forward.w1.biases": "model.safetensors",
231
+ "model.layers.19.feed_forward.w1.scales": "model.safetensors",
232
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
233
+ "model.layers.19.feed_forward.w2.biases": "model.safetensors",
234
+ "model.layers.19.feed_forward.w2.scales": "model.safetensors",
235
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
236
+ "model.layers.19.feed_forward.w3.biases": "model.safetensors",
237
+ "model.layers.19.feed_forward.w3.scales": "model.safetensors",
238
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
239
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
240
+ "model.layers.19.operator_norm.weight": "model.safetensors",
241
+ "model.layers.2.feed_forward.w1.biases": "model.safetensors",
242
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
243
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
244
+ "model.layers.2.feed_forward.w2.biases": "model.safetensors",
245
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
246
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
247
+ "model.layers.2.feed_forward.w3.biases": "model.safetensors",
248
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
249
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
250
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
251
+ "model.layers.2.operator_norm.weight": "model.safetensors",
252
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
253
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
254
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
255
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
257
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
258
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
259
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
260
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
261
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
262
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
263
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
264
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
265
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
266
+ "model.layers.20.conv.conv.weight": "model.safetensors",
267
+ "model.layers.20.conv.in_proj.biases": "model.safetensors",
268
+ "model.layers.20.conv.in_proj.scales": "model.safetensors",
269
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
270
+ "model.layers.20.conv.out_proj.biases": "model.safetensors",
271
+ "model.layers.20.conv.out_proj.scales": "model.safetensors",
272
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
273
+ "model.layers.20.feed_forward.w1.biases": "model.safetensors",
274
+ "model.layers.20.feed_forward.w1.scales": "model.safetensors",
275
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
276
+ "model.layers.20.feed_forward.w2.biases": "model.safetensors",
277
+ "model.layers.20.feed_forward.w2.scales": "model.safetensors",
278
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
279
+ "model.layers.20.feed_forward.w3.biases": "model.safetensors",
280
+ "model.layers.20.feed_forward.w3.scales": "model.safetensors",
281
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
282
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
283
+ "model.layers.20.operator_norm.weight": "model.safetensors",
284
+ "model.layers.21.feed_forward.w1.biases": "model.safetensors",
285
+ "model.layers.21.feed_forward.w1.scales": "model.safetensors",
286
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
287
+ "model.layers.21.feed_forward.w2.biases": "model.safetensors",
288
+ "model.layers.21.feed_forward.w2.scales": "model.safetensors",
289
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
290
+ "model.layers.21.feed_forward.w3.biases": "model.safetensors",
291
+ "model.layers.21.feed_forward.w3.scales": "model.safetensors",
292
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
293
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
294
+ "model.layers.21.operator_norm.weight": "model.safetensors",
295
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
296
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
297
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
298
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
299
+ "model.layers.21.self_attn.out_proj.biases": "model.safetensors",
300
+ "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
301
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
302
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
303
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
304
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
305
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
306
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.22.conv.conv.weight": "model.safetensors",
310
+ "model.layers.22.conv.in_proj.biases": "model.safetensors",
311
+ "model.layers.22.conv.in_proj.scales": "model.safetensors",
312
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
313
+ "model.layers.22.conv.out_proj.biases": "model.safetensors",
314
+ "model.layers.22.conv.out_proj.scales": "model.safetensors",
315
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
316
+ "model.layers.22.feed_forward.w1.biases": "model.safetensors",
317
+ "model.layers.22.feed_forward.w1.scales": "model.safetensors",
318
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
319
+ "model.layers.22.feed_forward.w2.biases": "model.safetensors",
320
+ "model.layers.22.feed_forward.w2.scales": "model.safetensors",
321
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
322
+ "model.layers.22.feed_forward.w3.biases": "model.safetensors",
323
+ "model.layers.22.feed_forward.w3.scales": "model.safetensors",
324
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
325
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
326
+ "model.layers.22.operator_norm.weight": "model.safetensors",
327
+ "model.layers.23.conv.conv.weight": "model.safetensors",
328
+ "model.layers.23.conv.in_proj.biases": "model.safetensors",
329
+ "model.layers.23.conv.in_proj.scales": "model.safetensors",
330
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
331
+ "model.layers.23.conv.out_proj.biases": "model.safetensors",
332
+ "model.layers.23.conv.out_proj.scales": "model.safetensors",
333
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
334
+ "model.layers.23.feed_forward.w1.biases": "model.safetensors",
335
+ "model.layers.23.feed_forward.w1.scales": "model.safetensors",
336
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
337
+ "model.layers.23.feed_forward.w2.biases": "model.safetensors",
338
+ "model.layers.23.feed_forward.w2.scales": "model.safetensors",
339
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
340
+ "model.layers.23.feed_forward.w3.biases": "model.safetensors",
341
+ "model.layers.23.feed_forward.w3.scales": "model.safetensors",
342
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
343
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
344
+ "model.layers.23.operator_norm.weight": "model.safetensors",
345
+ "model.layers.24.feed_forward.w1.biases": "model.safetensors",
346
+ "model.layers.24.feed_forward.w1.scales": "model.safetensors",
347
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
348
+ "model.layers.24.feed_forward.w2.biases": "model.safetensors",
349
+ "model.layers.24.feed_forward.w2.scales": "model.safetensors",
350
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
351
+ "model.layers.24.feed_forward.w3.biases": "model.safetensors",
352
+ "model.layers.24.feed_forward.w3.scales": "model.safetensors",
353
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
354
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
355
+ "model.layers.24.operator_norm.weight": "model.safetensors",
356
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
357
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
358
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
359
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
360
+ "model.layers.24.self_attn.out_proj.biases": "model.safetensors",
361
+ "model.layers.24.self_attn.out_proj.scales": "model.safetensors",
362
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
363
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
364
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
365
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
366
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
367
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
368
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
369
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
370
+ "model.layers.25.conv.conv.weight": "model.safetensors",
371
+ "model.layers.25.conv.in_proj.biases": "model.safetensors",
372
+ "model.layers.25.conv.in_proj.scales": "model.safetensors",
373
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
374
+ "model.layers.25.conv.out_proj.biases": "model.safetensors",
375
+ "model.layers.25.conv.out_proj.scales": "model.safetensors",
376
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
377
+ "model.layers.25.feed_forward.w1.biases": "model.safetensors",
378
+ "model.layers.25.feed_forward.w1.scales": "model.safetensors",
379
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
380
+ "model.layers.25.feed_forward.w2.biases": "model.safetensors",
381
+ "model.layers.25.feed_forward.w2.scales": "model.safetensors",
382
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
383
+ "model.layers.25.feed_forward.w3.biases": "model.safetensors",
384
+ "model.layers.25.feed_forward.w3.scales": "model.safetensors",
385
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
386
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
387
+ "model.layers.25.operator_norm.weight": "model.safetensors",
388
+ "model.layers.26.conv.conv.weight": "model.safetensors",
389
+ "model.layers.26.conv.in_proj.biases": "model.safetensors",
390
+ "model.layers.26.conv.in_proj.scales": "model.safetensors",
391
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
392
+ "model.layers.26.conv.out_proj.biases": "model.safetensors",
393
+ "model.layers.26.conv.out_proj.scales": "model.safetensors",
394
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
395
+ "model.layers.26.feed_forward.w1.biases": "model.safetensors",
396
+ "model.layers.26.feed_forward.w1.scales": "model.safetensors",
397
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
398
+ "model.layers.26.feed_forward.w2.biases": "model.safetensors",
399
+ "model.layers.26.feed_forward.w2.scales": "model.safetensors",
400
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
401
+ "model.layers.26.feed_forward.w3.biases": "model.safetensors",
402
+ "model.layers.26.feed_forward.w3.scales": "model.safetensors",
403
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
404
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
405
+ "model.layers.26.operator_norm.weight": "model.safetensors",
406
+ "model.layers.27.feed_forward.w1.biases": "model.safetensors",
407
+ "model.layers.27.feed_forward.w1.scales": "model.safetensors",
408
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
409
+ "model.layers.27.feed_forward.w2.biases": "model.safetensors",
410
+ "model.layers.27.feed_forward.w2.scales": "model.safetensors",
411
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
412
+ "model.layers.27.feed_forward.w3.biases": "model.safetensors",
413
+ "model.layers.27.feed_forward.w3.scales": "model.safetensors",
414
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
415
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
416
+ "model.layers.27.operator_norm.weight": "model.safetensors",
417
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
418
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
419
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
420
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
421
+ "model.layers.27.self_attn.out_proj.biases": "model.safetensors",
422
+ "model.layers.27.self_attn.out_proj.scales": "model.safetensors",
423
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
424
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
425
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
426
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
427
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
428
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
429
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
430
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
431
+ "model.layers.28.conv.conv.weight": "model.safetensors",
432
+ "model.layers.28.conv.in_proj.biases": "model.safetensors",
433
+ "model.layers.28.conv.in_proj.scales": "model.safetensors",
434
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
435
+ "model.layers.28.conv.out_proj.biases": "model.safetensors",
436
+ "model.layers.28.conv.out_proj.scales": "model.safetensors",
437
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
438
+ "model.layers.28.feed_forward.w1.biases": "model.safetensors",
439
+ "model.layers.28.feed_forward.w1.scales": "model.safetensors",
440
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
441
+ "model.layers.28.feed_forward.w2.biases": "model.safetensors",
442
+ "model.layers.28.feed_forward.w2.scales": "model.safetensors",
443
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
444
+ "model.layers.28.feed_forward.w3.biases": "model.safetensors",
445
+ "model.layers.28.feed_forward.w3.scales": "model.safetensors",
446
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
447
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
448
+ "model.layers.28.operator_norm.weight": "model.safetensors",
449
+ "model.layers.29.conv.conv.weight": "model.safetensors",
450
+ "model.layers.29.conv.in_proj.biases": "model.safetensors",
451
+ "model.layers.29.conv.in_proj.scales": "model.safetensors",
452
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
453
+ "model.layers.29.conv.out_proj.biases": "model.safetensors",
454
+ "model.layers.29.conv.out_proj.scales": "model.safetensors",
455
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
456
+ "model.layers.29.feed_forward.w1.biases": "model.safetensors",
457
+ "model.layers.29.feed_forward.w1.scales": "model.safetensors",
458
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
459
+ "model.layers.29.feed_forward.w2.biases": "model.safetensors",
460
+ "model.layers.29.feed_forward.w2.scales": "model.safetensors",
461
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
462
+ "model.layers.29.feed_forward.w3.biases": "model.safetensors",
463
+ "model.layers.29.feed_forward.w3.scales": "model.safetensors",
464
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
465
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
466
+ "model.layers.29.operator_norm.weight": "model.safetensors",
467
+ "model.layers.3.conv.conv.weight": "model.safetensors",
468
+ "model.layers.3.conv.in_proj.biases": "model.safetensors",
469
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
470
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
471
+ "model.layers.3.conv.out_proj.biases": "model.safetensors",
472
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
473
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
474
+ "model.layers.3.feed_forward.w1.biases": "model.safetensors",
475
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
476
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
477
+ "model.layers.3.feed_forward.w2.biases": "model.safetensors",
478
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
479
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
480
+ "model.layers.3.feed_forward.w3.biases": "model.safetensors",
481
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
482
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
483
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
484
+ "model.layers.3.operator_norm.weight": "model.safetensors",
485
+ "model.layers.4.conv.conv.weight": "model.safetensors",
486
+ "model.layers.4.conv.in_proj.biases": "model.safetensors",
487
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
488
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
489
+ "model.layers.4.conv.out_proj.biases": "model.safetensors",
490
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
491
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
492
+ "model.layers.4.feed_forward.w1.biases": "model.safetensors",
493
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
494
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
495
+ "model.layers.4.feed_forward.w2.biases": "model.safetensors",
496
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
497
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
498
+ "model.layers.4.feed_forward.w3.biases": "model.safetensors",
499
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
500
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
501
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
502
+ "model.layers.4.operator_norm.weight": "model.safetensors",
503
+ "model.layers.5.feed_forward.w1.biases": "model.safetensors",
504
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
505
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
506
+ "model.layers.5.feed_forward.w2.biases": "model.safetensors",
507
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
508
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
509
+ "model.layers.5.feed_forward.w3.biases": "model.safetensors",
510
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
511
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
512
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
513
+ "model.layers.5.operator_norm.weight": "model.safetensors",
514
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
515
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
+ "model.layers.5.self_attn.out_proj.biases": "model.safetensors",
519
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
520
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
521
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
522
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
526
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
527
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
528
+ "model.layers.6.conv.conv.weight": "model.safetensors",
529
+ "model.layers.6.conv.in_proj.biases": "model.safetensors",
530
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
531
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
532
+ "model.layers.6.conv.out_proj.biases": "model.safetensors",
533
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
534
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
535
+ "model.layers.6.feed_forward.w1.biases": "model.safetensors",
536
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
537
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
538
+ "model.layers.6.feed_forward.w2.biases": "model.safetensors",
539
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
540
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
541
+ "model.layers.6.feed_forward.w3.biases": "model.safetensors",
542
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
543
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
544
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
545
+ "model.layers.6.operator_norm.weight": "model.safetensors",
546
+ "model.layers.7.conv.conv.weight": "model.safetensors",
547
+ "model.layers.7.conv.in_proj.biases": "model.safetensors",
548
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
549
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
550
+ "model.layers.7.conv.out_proj.biases": "model.safetensors",
551
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
552
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
553
+ "model.layers.7.feed_forward.w1.biases": "model.safetensors",
554
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
555
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
556
+ "model.layers.7.feed_forward.w2.biases": "model.safetensors",
557
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
558
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
559
+ "model.layers.7.feed_forward.w3.biases": "model.safetensors",
560
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
561
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
562
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
563
+ "model.layers.7.operator_norm.weight": "model.safetensors",
564
+ "model.layers.8.conv.conv.weight": "model.safetensors",
565
+ "model.layers.8.conv.in_proj.biases": "model.safetensors",
566
+ "model.layers.8.conv.in_proj.scales": "model.safetensors",
567
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
568
+ "model.layers.8.conv.out_proj.biases": "model.safetensors",
569
+ "model.layers.8.conv.out_proj.scales": "model.safetensors",
570
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
571
+ "model.layers.8.feed_forward.w1.biases": "model.safetensors",
572
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
573
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
574
+ "model.layers.8.feed_forward.w2.biases": "model.safetensors",
575
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
576
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
577
+ "model.layers.8.feed_forward.w3.biases": "model.safetensors",
578
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
579
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
580
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
581
+ "model.layers.8.operator_norm.weight": "model.safetensors",
582
+ "model.layers.9.feed_forward.w1.biases": "model.safetensors",
583
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
584
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
585
+ "model.layers.9.feed_forward.w2.biases": "model.safetensors",
586
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
587
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
588
+ "model.layers.9.feed_forward.w3.biases": "model.safetensors",
589
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
590
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
591
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
592
+ "model.layers.9.operator_norm.weight": "model.safetensors",
593
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
594
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
595
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
596
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
597
+ "model.layers.9.self_attn.out_proj.biases": "model.safetensors",
598
+ "model.layers.9.self_attn.out_proj.scales": "model.safetensors",
599
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
600
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
601
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
602
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
603
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
604
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
605
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
606
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
607
+ }
608
+ }
4bit/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
4bit/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
5bit/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
5bit/config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 64,
69
+ "bits": 5,
70
+ "mode": "affine",
71
+ "model.embed_tokens": {
72
+ "group_size": 64,
73
+ "bits": 6,
74
+ "mode": "affine"
75
+ }
76
+ },
77
+ "quantization_config": {
78
+ "group_size": 64,
79
+ "bits": 5,
80
+ "mode": "affine",
81
+ "model.embed_tokens": {
82
+ "group_size": 64,
83
+ "bits": 6,
84
+ "mode": "affine"
85
+ }
86
+ },
87
+ "rope_parameters": {
88
+ "rope_theta": 10000000.0,
89
+ "rope_type": "default"
90
+ },
91
+ "rope_theta": 10000000.0,
92
+ "tie_word_embeddings": true,
93
+ "transformers_version": "5.2.0",
94
+ "use_cache": true,
95
+ "use_pos_enc": true,
96
+ "vocab_size": 128000
97
+ }
5bit/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
5bit/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efa4a08f654363636805a2909848a8515c983d50a9896feb89fc4a66ffc4d51
3
+ size 1887502256
5bit/model.safetensors.index.json ADDED
@@ -0,0 +1,608 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1887434752,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.embedding_norm.weight": "model.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
18
+ "model.layers.0.feed_forward.w1.biases": "model.safetensors",
19
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.0.feed_forward.w2.biases": "model.safetensors",
22
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
23
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
24
+ "model.layers.0.feed_forward.w3.biases": "model.safetensors",
25
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
26
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.1.feed_forward.w1.biases": "model.safetensors",
37
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
38
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
39
+ "model.layers.1.feed_forward.w2.biases": "model.safetensors",
40
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
41
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
42
+ "model.layers.1.feed_forward.w3.biases": "model.safetensors",
43
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
44
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model.safetensors",
47
+ "model.layers.10.conv.conv.weight": "model.safetensors",
48
+ "model.layers.10.conv.in_proj.biases": "model.safetensors",
49
+ "model.layers.10.conv.in_proj.scales": "model.safetensors",
50
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
51
+ "model.layers.10.conv.out_proj.biases": "model.safetensors",
52
+ "model.layers.10.conv.out_proj.scales": "model.safetensors",
53
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
54
+ "model.layers.10.feed_forward.w1.biases": "model.safetensors",
55
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
56
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
57
+ "model.layers.10.feed_forward.w2.biases": "model.safetensors",
58
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
59
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
60
+ "model.layers.10.feed_forward.w3.biases": "model.safetensors",
61
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
62
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
63
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
64
+ "model.layers.10.operator_norm.weight": "model.safetensors",
65
+ "model.layers.11.conv.conv.weight": "model.safetensors",
66
+ "model.layers.11.conv.in_proj.biases": "model.safetensors",
67
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
68
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
69
+ "model.layers.11.conv.out_proj.biases": "model.safetensors",
70
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
71
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
72
+ "model.layers.11.feed_forward.w1.biases": "model.safetensors",
73
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
74
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
75
+ "model.layers.11.feed_forward.w2.biases": "model.safetensors",
76
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
77
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
78
+ "model.layers.11.feed_forward.w3.biases": "model.safetensors",
79
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
80
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
81
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
82
+ "model.layers.11.operator_norm.weight": "model.safetensors",
83
+ "model.layers.12.conv.conv.weight": "model.safetensors",
84
+ "model.layers.12.conv.in_proj.biases": "model.safetensors",
85
+ "model.layers.12.conv.in_proj.scales": "model.safetensors",
86
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
87
+ "model.layers.12.conv.out_proj.biases": "model.safetensors",
88
+ "model.layers.12.conv.out_proj.scales": "model.safetensors",
89
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
90
+ "model.layers.12.feed_forward.w1.biases": "model.safetensors",
91
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
92
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
93
+ "model.layers.12.feed_forward.w2.biases": "model.safetensors",
94
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
95
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
96
+ "model.layers.12.feed_forward.w3.biases": "model.safetensors",
97
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
98
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
99
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
100
+ "model.layers.12.operator_norm.weight": "model.safetensors",
101
+ "model.layers.13.feed_forward.w1.biases": "model.safetensors",
102
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
103
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
104
+ "model.layers.13.feed_forward.w2.biases": "model.safetensors",
105
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
106
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
107
+ "model.layers.13.feed_forward.w3.biases": "model.safetensors",
108
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
109
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
110
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
111
+ "model.layers.13.operator_norm.weight": "model.safetensors",
112
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
113
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
114
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
115
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
116
+ "model.layers.13.self_attn.out_proj.biases": "model.safetensors",
117
+ "model.layers.13.self_attn.out_proj.scales": "model.safetensors",
118
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
119
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
120
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
121
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
122
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
124
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
125
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
126
+ "model.layers.14.conv.conv.weight": "model.safetensors",
127
+ "model.layers.14.conv.in_proj.biases": "model.safetensors",
128
+ "model.layers.14.conv.in_proj.scales": "model.safetensors",
129
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
130
+ "model.layers.14.conv.out_proj.biases": "model.safetensors",
131
+ "model.layers.14.conv.out_proj.scales": "model.safetensors",
132
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
133
+ "model.layers.14.feed_forward.w1.biases": "model.safetensors",
134
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
135
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
136
+ "model.layers.14.feed_forward.w2.biases": "model.safetensors",
137
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
138
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
139
+ "model.layers.14.feed_forward.w3.biases": "model.safetensors",
140
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
141
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
142
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
143
+ "model.layers.14.operator_norm.weight": "model.safetensors",
144
+ "model.layers.15.conv.conv.weight": "model.safetensors",
145
+ "model.layers.15.conv.in_proj.biases": "model.safetensors",
146
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
147
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
148
+ "model.layers.15.conv.out_proj.biases": "model.safetensors",
149
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
150
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
151
+ "model.layers.15.feed_forward.w1.biases": "model.safetensors",
152
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
153
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
154
+ "model.layers.15.feed_forward.w2.biases": "model.safetensors",
155
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
156
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
157
+ "model.layers.15.feed_forward.w3.biases": "model.safetensors",
158
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
159
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
160
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
161
+ "model.layers.15.operator_norm.weight": "model.safetensors",
162
+ "model.layers.16.conv.conv.weight": "model.safetensors",
163
+ "model.layers.16.conv.in_proj.biases": "model.safetensors",
164
+ "model.layers.16.conv.in_proj.scales": "model.safetensors",
165
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
166
+ "model.layers.16.conv.out_proj.biases": "model.safetensors",
167
+ "model.layers.16.conv.out_proj.scales": "model.safetensors",
168
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
169
+ "model.layers.16.feed_forward.w1.biases": "model.safetensors",
170
+ "model.layers.16.feed_forward.w1.scales": "model.safetensors",
171
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
172
+ "model.layers.16.feed_forward.w2.biases": "model.safetensors",
173
+ "model.layers.16.feed_forward.w2.scales": "model.safetensors",
174
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
175
+ "model.layers.16.feed_forward.w3.biases": "model.safetensors",
176
+ "model.layers.16.feed_forward.w3.scales": "model.safetensors",
177
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
178
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
179
+ "model.layers.16.operator_norm.weight": "model.safetensors",
180
+ "model.layers.17.feed_forward.w1.biases": "model.safetensors",
181
+ "model.layers.17.feed_forward.w1.scales": "model.safetensors",
182
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
183
+ "model.layers.17.feed_forward.w2.biases": "model.safetensors",
184
+ "model.layers.17.feed_forward.w2.scales": "model.safetensors",
185
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
186
+ "model.layers.17.feed_forward.w3.biases": "model.safetensors",
187
+ "model.layers.17.feed_forward.w3.scales": "model.safetensors",
188
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
189
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
190
+ "model.layers.17.operator_norm.weight": "model.safetensors",
191
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
192
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
193
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
194
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
195
+ "model.layers.17.self_attn.out_proj.biases": "model.safetensors",
196
+ "model.layers.17.self_attn.out_proj.scales": "model.safetensors",
197
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
198
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
199
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
200
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
201
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
202
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
203
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
204
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
205
+ "model.layers.18.conv.conv.weight": "model.safetensors",
206
+ "model.layers.18.conv.in_proj.biases": "model.safetensors",
207
+ "model.layers.18.conv.in_proj.scales": "model.safetensors",
208
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
209
+ "model.layers.18.conv.out_proj.biases": "model.safetensors",
210
+ "model.layers.18.conv.out_proj.scales": "model.safetensors",
211
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
212
+ "model.layers.18.feed_forward.w1.biases": "model.safetensors",
213
+ "model.layers.18.feed_forward.w1.scales": "model.safetensors",
214
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
215
+ "model.layers.18.feed_forward.w2.biases": "model.safetensors",
216
+ "model.layers.18.feed_forward.w2.scales": "model.safetensors",
217
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
218
+ "model.layers.18.feed_forward.w3.biases": "model.safetensors",
219
+ "model.layers.18.feed_forward.w3.scales": "model.safetensors",
220
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
221
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
222
+ "model.layers.18.operator_norm.weight": "model.safetensors",
223
+ "model.layers.19.conv.conv.weight": "model.safetensors",
224
+ "model.layers.19.conv.in_proj.biases": "model.safetensors",
225
+ "model.layers.19.conv.in_proj.scales": "model.safetensors",
226
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
227
+ "model.layers.19.conv.out_proj.biases": "model.safetensors",
228
+ "model.layers.19.conv.out_proj.scales": "model.safetensors",
229
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
230
+ "model.layers.19.feed_forward.w1.biases": "model.safetensors",
231
+ "model.layers.19.feed_forward.w1.scales": "model.safetensors",
232
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
233
+ "model.layers.19.feed_forward.w2.biases": "model.safetensors",
234
+ "model.layers.19.feed_forward.w2.scales": "model.safetensors",
235
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
236
+ "model.layers.19.feed_forward.w3.biases": "model.safetensors",
237
+ "model.layers.19.feed_forward.w3.scales": "model.safetensors",
238
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
239
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
240
+ "model.layers.19.operator_norm.weight": "model.safetensors",
241
+ "model.layers.2.feed_forward.w1.biases": "model.safetensors",
242
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
243
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
244
+ "model.layers.2.feed_forward.w2.biases": "model.safetensors",
245
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
246
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
247
+ "model.layers.2.feed_forward.w3.biases": "model.safetensors",
248
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
249
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
250
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
251
+ "model.layers.2.operator_norm.weight": "model.safetensors",
252
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
253
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
254
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
255
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
257
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
258
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
259
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
260
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
261
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
262
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
263
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
264
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
265
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
266
+ "model.layers.20.conv.conv.weight": "model.safetensors",
267
+ "model.layers.20.conv.in_proj.biases": "model.safetensors",
268
+ "model.layers.20.conv.in_proj.scales": "model.safetensors",
269
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
270
+ "model.layers.20.conv.out_proj.biases": "model.safetensors",
271
+ "model.layers.20.conv.out_proj.scales": "model.safetensors",
272
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
273
+ "model.layers.20.feed_forward.w1.biases": "model.safetensors",
274
+ "model.layers.20.feed_forward.w1.scales": "model.safetensors",
275
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
276
+ "model.layers.20.feed_forward.w2.biases": "model.safetensors",
277
+ "model.layers.20.feed_forward.w2.scales": "model.safetensors",
278
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
279
+ "model.layers.20.feed_forward.w3.biases": "model.safetensors",
280
+ "model.layers.20.feed_forward.w3.scales": "model.safetensors",
281
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
282
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
283
+ "model.layers.20.operator_norm.weight": "model.safetensors",
284
+ "model.layers.21.feed_forward.w1.biases": "model.safetensors",
285
+ "model.layers.21.feed_forward.w1.scales": "model.safetensors",
286
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
287
+ "model.layers.21.feed_forward.w2.biases": "model.safetensors",
288
+ "model.layers.21.feed_forward.w2.scales": "model.safetensors",
289
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
290
+ "model.layers.21.feed_forward.w3.biases": "model.safetensors",
291
+ "model.layers.21.feed_forward.w3.scales": "model.safetensors",
292
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
293
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
294
+ "model.layers.21.operator_norm.weight": "model.safetensors",
295
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
296
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
297
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
298
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
299
+ "model.layers.21.self_attn.out_proj.biases": "model.safetensors",
300
+ "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
301
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
302
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
303
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
304
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
305
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
306
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.22.conv.conv.weight": "model.safetensors",
310
+ "model.layers.22.conv.in_proj.biases": "model.safetensors",
311
+ "model.layers.22.conv.in_proj.scales": "model.safetensors",
312
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
313
+ "model.layers.22.conv.out_proj.biases": "model.safetensors",
314
+ "model.layers.22.conv.out_proj.scales": "model.safetensors",
315
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
316
+ "model.layers.22.feed_forward.w1.biases": "model.safetensors",
317
+ "model.layers.22.feed_forward.w1.scales": "model.safetensors",
318
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
319
+ "model.layers.22.feed_forward.w2.biases": "model.safetensors",
320
+ "model.layers.22.feed_forward.w2.scales": "model.safetensors",
321
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
322
+ "model.layers.22.feed_forward.w3.biases": "model.safetensors",
323
+ "model.layers.22.feed_forward.w3.scales": "model.safetensors",
324
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
325
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
326
+ "model.layers.22.operator_norm.weight": "model.safetensors",
327
+ "model.layers.23.conv.conv.weight": "model.safetensors",
328
+ "model.layers.23.conv.in_proj.biases": "model.safetensors",
329
+ "model.layers.23.conv.in_proj.scales": "model.safetensors",
330
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
331
+ "model.layers.23.conv.out_proj.biases": "model.safetensors",
332
+ "model.layers.23.conv.out_proj.scales": "model.safetensors",
333
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
334
+ "model.layers.23.feed_forward.w1.biases": "model.safetensors",
335
+ "model.layers.23.feed_forward.w1.scales": "model.safetensors",
336
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
337
+ "model.layers.23.feed_forward.w2.biases": "model.safetensors",
338
+ "model.layers.23.feed_forward.w2.scales": "model.safetensors",
339
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
340
+ "model.layers.23.feed_forward.w3.biases": "model.safetensors",
341
+ "model.layers.23.feed_forward.w3.scales": "model.safetensors",
342
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
343
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
344
+ "model.layers.23.operator_norm.weight": "model.safetensors",
345
+ "model.layers.24.feed_forward.w1.biases": "model.safetensors",
346
+ "model.layers.24.feed_forward.w1.scales": "model.safetensors",
347
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
348
+ "model.layers.24.feed_forward.w2.biases": "model.safetensors",
349
+ "model.layers.24.feed_forward.w2.scales": "model.safetensors",
350
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
351
+ "model.layers.24.feed_forward.w3.biases": "model.safetensors",
352
+ "model.layers.24.feed_forward.w3.scales": "model.safetensors",
353
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
354
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
355
+ "model.layers.24.operator_norm.weight": "model.safetensors",
356
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
357
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
358
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
359
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
360
+ "model.layers.24.self_attn.out_proj.biases": "model.safetensors",
361
+ "model.layers.24.self_attn.out_proj.scales": "model.safetensors",
362
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
363
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
364
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
365
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
366
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
367
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
368
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
369
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
370
+ "model.layers.25.conv.conv.weight": "model.safetensors",
371
+ "model.layers.25.conv.in_proj.biases": "model.safetensors",
372
+ "model.layers.25.conv.in_proj.scales": "model.safetensors",
373
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
374
+ "model.layers.25.conv.out_proj.biases": "model.safetensors",
375
+ "model.layers.25.conv.out_proj.scales": "model.safetensors",
376
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
377
+ "model.layers.25.feed_forward.w1.biases": "model.safetensors",
378
+ "model.layers.25.feed_forward.w1.scales": "model.safetensors",
379
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
380
+ "model.layers.25.feed_forward.w2.biases": "model.safetensors",
381
+ "model.layers.25.feed_forward.w2.scales": "model.safetensors",
382
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
383
+ "model.layers.25.feed_forward.w3.biases": "model.safetensors",
384
+ "model.layers.25.feed_forward.w3.scales": "model.safetensors",
385
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
386
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
387
+ "model.layers.25.operator_norm.weight": "model.safetensors",
388
+ "model.layers.26.conv.conv.weight": "model.safetensors",
389
+ "model.layers.26.conv.in_proj.biases": "model.safetensors",
390
+ "model.layers.26.conv.in_proj.scales": "model.safetensors",
391
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
392
+ "model.layers.26.conv.out_proj.biases": "model.safetensors",
393
+ "model.layers.26.conv.out_proj.scales": "model.safetensors",
394
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
395
+ "model.layers.26.feed_forward.w1.biases": "model.safetensors",
396
+ "model.layers.26.feed_forward.w1.scales": "model.safetensors",
397
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
398
+ "model.layers.26.feed_forward.w2.biases": "model.safetensors",
399
+ "model.layers.26.feed_forward.w2.scales": "model.safetensors",
400
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
401
+ "model.layers.26.feed_forward.w3.biases": "model.safetensors",
402
+ "model.layers.26.feed_forward.w3.scales": "model.safetensors",
403
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
404
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
405
+ "model.layers.26.operator_norm.weight": "model.safetensors",
406
+ "model.layers.27.feed_forward.w1.biases": "model.safetensors",
407
+ "model.layers.27.feed_forward.w1.scales": "model.safetensors",
408
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
409
+ "model.layers.27.feed_forward.w2.biases": "model.safetensors",
410
+ "model.layers.27.feed_forward.w2.scales": "model.safetensors",
411
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
412
+ "model.layers.27.feed_forward.w3.biases": "model.safetensors",
413
+ "model.layers.27.feed_forward.w3.scales": "model.safetensors",
414
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
415
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
416
+ "model.layers.27.operator_norm.weight": "model.safetensors",
417
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
418
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
419
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
420
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
421
+ "model.layers.27.self_attn.out_proj.biases": "model.safetensors",
422
+ "model.layers.27.self_attn.out_proj.scales": "model.safetensors",
423
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
424
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
425
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
426
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
427
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
428
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
429
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
430
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
431
+ "model.layers.28.conv.conv.weight": "model.safetensors",
432
+ "model.layers.28.conv.in_proj.biases": "model.safetensors",
433
+ "model.layers.28.conv.in_proj.scales": "model.safetensors",
434
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
435
+ "model.layers.28.conv.out_proj.biases": "model.safetensors",
436
+ "model.layers.28.conv.out_proj.scales": "model.safetensors",
437
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
438
+ "model.layers.28.feed_forward.w1.biases": "model.safetensors",
439
+ "model.layers.28.feed_forward.w1.scales": "model.safetensors",
440
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
441
+ "model.layers.28.feed_forward.w2.biases": "model.safetensors",
442
+ "model.layers.28.feed_forward.w2.scales": "model.safetensors",
443
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
444
+ "model.layers.28.feed_forward.w3.biases": "model.safetensors",
445
+ "model.layers.28.feed_forward.w3.scales": "model.safetensors",
446
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
447
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
448
+ "model.layers.28.operator_norm.weight": "model.safetensors",
449
+ "model.layers.29.conv.conv.weight": "model.safetensors",
450
+ "model.layers.29.conv.in_proj.biases": "model.safetensors",
451
+ "model.layers.29.conv.in_proj.scales": "model.safetensors",
452
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
453
+ "model.layers.29.conv.out_proj.biases": "model.safetensors",
454
+ "model.layers.29.conv.out_proj.scales": "model.safetensors",
455
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
456
+ "model.layers.29.feed_forward.w1.biases": "model.safetensors",
457
+ "model.layers.29.feed_forward.w1.scales": "model.safetensors",
458
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
459
+ "model.layers.29.feed_forward.w2.biases": "model.safetensors",
460
+ "model.layers.29.feed_forward.w2.scales": "model.safetensors",
461
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
462
+ "model.layers.29.feed_forward.w3.biases": "model.safetensors",
463
+ "model.layers.29.feed_forward.w3.scales": "model.safetensors",
464
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
465
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
466
+ "model.layers.29.operator_norm.weight": "model.safetensors",
467
+ "model.layers.3.conv.conv.weight": "model.safetensors",
468
+ "model.layers.3.conv.in_proj.biases": "model.safetensors",
469
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
470
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
471
+ "model.layers.3.conv.out_proj.biases": "model.safetensors",
472
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
473
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
474
+ "model.layers.3.feed_forward.w1.biases": "model.safetensors",
475
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
476
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
477
+ "model.layers.3.feed_forward.w2.biases": "model.safetensors",
478
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
479
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
480
+ "model.layers.3.feed_forward.w3.biases": "model.safetensors",
481
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
482
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
483
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
484
+ "model.layers.3.operator_norm.weight": "model.safetensors",
485
+ "model.layers.4.conv.conv.weight": "model.safetensors",
486
+ "model.layers.4.conv.in_proj.biases": "model.safetensors",
487
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
488
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
489
+ "model.layers.4.conv.out_proj.biases": "model.safetensors",
490
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
491
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
492
+ "model.layers.4.feed_forward.w1.biases": "model.safetensors",
493
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
494
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
495
+ "model.layers.4.feed_forward.w2.biases": "model.safetensors",
496
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
497
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
498
+ "model.layers.4.feed_forward.w3.biases": "model.safetensors",
499
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
500
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
501
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
502
+ "model.layers.4.operator_norm.weight": "model.safetensors",
503
+ "model.layers.5.feed_forward.w1.biases": "model.safetensors",
504
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
505
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
506
+ "model.layers.5.feed_forward.w2.biases": "model.safetensors",
507
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
508
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
509
+ "model.layers.5.feed_forward.w3.biases": "model.safetensors",
510
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
511
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
512
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
513
+ "model.layers.5.operator_norm.weight": "model.safetensors",
514
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
515
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
+ "model.layers.5.self_attn.out_proj.biases": "model.safetensors",
519
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
520
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
521
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
522
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
526
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
527
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
528
+ "model.layers.6.conv.conv.weight": "model.safetensors",
529
+ "model.layers.6.conv.in_proj.biases": "model.safetensors",
530
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
531
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
532
+ "model.layers.6.conv.out_proj.biases": "model.safetensors",
533
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
534
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
535
+ "model.layers.6.feed_forward.w1.biases": "model.safetensors",
536
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
537
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
538
+ "model.layers.6.feed_forward.w2.biases": "model.safetensors",
539
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
540
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
541
+ "model.layers.6.feed_forward.w3.biases": "model.safetensors",
542
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
543
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
544
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
545
+ "model.layers.6.operator_norm.weight": "model.safetensors",
546
+ "model.layers.7.conv.conv.weight": "model.safetensors",
547
+ "model.layers.7.conv.in_proj.biases": "model.safetensors",
548
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
549
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
550
+ "model.layers.7.conv.out_proj.biases": "model.safetensors",
551
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
552
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
553
+ "model.layers.7.feed_forward.w1.biases": "model.safetensors",
554
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
555
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
556
+ "model.layers.7.feed_forward.w2.biases": "model.safetensors",
557
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
558
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
559
+ "model.layers.7.feed_forward.w3.biases": "model.safetensors",
560
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
561
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
562
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
563
+ "model.layers.7.operator_norm.weight": "model.safetensors",
564
+ "model.layers.8.conv.conv.weight": "model.safetensors",
565
+ "model.layers.8.conv.in_proj.biases": "model.safetensors",
566
+ "model.layers.8.conv.in_proj.scales": "model.safetensors",
567
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
568
+ "model.layers.8.conv.out_proj.biases": "model.safetensors",
569
+ "model.layers.8.conv.out_proj.scales": "model.safetensors",
570
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
571
+ "model.layers.8.feed_forward.w1.biases": "model.safetensors",
572
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
573
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
574
+ "model.layers.8.feed_forward.w2.biases": "model.safetensors",
575
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
576
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
577
+ "model.layers.8.feed_forward.w3.biases": "model.safetensors",
578
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
579
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
580
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
581
+ "model.layers.8.operator_norm.weight": "model.safetensors",
582
+ "model.layers.9.feed_forward.w1.biases": "model.safetensors",
583
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
584
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
585
+ "model.layers.9.feed_forward.w2.biases": "model.safetensors",
586
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
587
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
588
+ "model.layers.9.feed_forward.w3.biases": "model.safetensors",
589
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
590
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
591
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
592
+ "model.layers.9.operator_norm.weight": "model.safetensors",
593
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
594
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
595
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
596
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
597
+ "model.layers.9.self_attn.out_proj.biases": "model.safetensors",
598
+ "model.layers.9.self_attn.out_proj.scales": "model.safetensors",
599
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
600
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
601
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
602
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
603
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
604
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
605
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
606
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
607
+ }
608
+ }
5bit/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
5bit/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
6bit/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
6bit/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 64,
69
+ "bits": 6,
70
+ "mode": "affine"
71
+ },
72
+ "quantization_config": {
73
+ "group_size": 64,
74
+ "bits": 6,
75
+ "mode": "affine"
76
+ },
77
+ "rope_parameters": {
78
+ "rope_theta": 10000000.0,
79
+ "rope_type": "default"
80
+ },
81
+ "rope_theta": 10000000.0,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.2.0",
84
+ "use_cache": true,
85
+ "use_pos_enc": true,
86
+ "vocab_size": 128000
87
+ }
6bit/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
6bit/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c78541214b57816a6b97b7676db7943b036b65b6edfce5fdf0181bb76b25646a
3
+ size 2191851544
6bit/model.safetensors.index.json ADDED
@@ -0,0 +1,608 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2191783936,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.embedding_norm.weight": "model.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
18
+ "model.layers.0.feed_forward.w1.biases": "model.safetensors",
19
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.0.feed_forward.w2.biases": "model.safetensors",
22
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
23
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
24
+ "model.layers.0.feed_forward.w3.biases": "model.safetensors",
25
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
26
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.1.feed_forward.w1.biases": "model.safetensors",
37
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
38
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
39
+ "model.layers.1.feed_forward.w2.biases": "model.safetensors",
40
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
41
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
42
+ "model.layers.1.feed_forward.w3.biases": "model.safetensors",
43
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
44
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model.safetensors",
47
+ "model.layers.10.conv.conv.weight": "model.safetensors",
48
+ "model.layers.10.conv.in_proj.biases": "model.safetensors",
49
+ "model.layers.10.conv.in_proj.scales": "model.safetensors",
50
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
51
+ "model.layers.10.conv.out_proj.biases": "model.safetensors",
52
+ "model.layers.10.conv.out_proj.scales": "model.safetensors",
53
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
54
+ "model.layers.10.feed_forward.w1.biases": "model.safetensors",
55
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
56
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
57
+ "model.layers.10.feed_forward.w2.biases": "model.safetensors",
58
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
59
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
60
+ "model.layers.10.feed_forward.w3.biases": "model.safetensors",
61
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
62
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
63
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
64
+ "model.layers.10.operator_norm.weight": "model.safetensors",
65
+ "model.layers.11.conv.conv.weight": "model.safetensors",
66
+ "model.layers.11.conv.in_proj.biases": "model.safetensors",
67
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
68
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
69
+ "model.layers.11.conv.out_proj.biases": "model.safetensors",
70
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
71
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
72
+ "model.layers.11.feed_forward.w1.biases": "model.safetensors",
73
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
74
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
75
+ "model.layers.11.feed_forward.w2.biases": "model.safetensors",
76
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
77
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
78
+ "model.layers.11.feed_forward.w3.biases": "model.safetensors",
79
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
80
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
81
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
82
+ "model.layers.11.operator_norm.weight": "model.safetensors",
83
+ "model.layers.12.conv.conv.weight": "model.safetensors",
84
+ "model.layers.12.conv.in_proj.biases": "model.safetensors",
85
+ "model.layers.12.conv.in_proj.scales": "model.safetensors",
86
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
87
+ "model.layers.12.conv.out_proj.biases": "model.safetensors",
88
+ "model.layers.12.conv.out_proj.scales": "model.safetensors",
89
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
90
+ "model.layers.12.feed_forward.w1.biases": "model.safetensors",
91
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
92
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
93
+ "model.layers.12.feed_forward.w2.biases": "model.safetensors",
94
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
95
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
96
+ "model.layers.12.feed_forward.w3.biases": "model.safetensors",
97
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
98
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
99
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
100
+ "model.layers.12.operator_norm.weight": "model.safetensors",
101
+ "model.layers.13.feed_forward.w1.biases": "model.safetensors",
102
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
103
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
104
+ "model.layers.13.feed_forward.w2.biases": "model.safetensors",
105
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
106
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
107
+ "model.layers.13.feed_forward.w3.biases": "model.safetensors",
108
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
109
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
110
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
111
+ "model.layers.13.operator_norm.weight": "model.safetensors",
112
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
113
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
114
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
115
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
116
+ "model.layers.13.self_attn.out_proj.biases": "model.safetensors",
117
+ "model.layers.13.self_attn.out_proj.scales": "model.safetensors",
118
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
119
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
120
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
121
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
122
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
124
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
125
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
126
+ "model.layers.14.conv.conv.weight": "model.safetensors",
127
+ "model.layers.14.conv.in_proj.biases": "model.safetensors",
128
+ "model.layers.14.conv.in_proj.scales": "model.safetensors",
129
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
130
+ "model.layers.14.conv.out_proj.biases": "model.safetensors",
131
+ "model.layers.14.conv.out_proj.scales": "model.safetensors",
132
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
133
+ "model.layers.14.feed_forward.w1.biases": "model.safetensors",
134
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
135
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
136
+ "model.layers.14.feed_forward.w2.biases": "model.safetensors",
137
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
138
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
139
+ "model.layers.14.feed_forward.w3.biases": "model.safetensors",
140
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
141
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
142
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
143
+ "model.layers.14.operator_norm.weight": "model.safetensors",
144
+ "model.layers.15.conv.conv.weight": "model.safetensors",
145
+ "model.layers.15.conv.in_proj.biases": "model.safetensors",
146
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
147
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
148
+ "model.layers.15.conv.out_proj.biases": "model.safetensors",
149
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
150
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
151
+ "model.layers.15.feed_forward.w1.biases": "model.safetensors",
152
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
153
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
154
+ "model.layers.15.feed_forward.w2.biases": "model.safetensors",
155
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
156
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
157
+ "model.layers.15.feed_forward.w3.biases": "model.safetensors",
158
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
159
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
160
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
161
+ "model.layers.15.operator_norm.weight": "model.safetensors",
162
+ "model.layers.16.conv.conv.weight": "model.safetensors",
163
+ "model.layers.16.conv.in_proj.biases": "model.safetensors",
164
+ "model.layers.16.conv.in_proj.scales": "model.safetensors",
165
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
166
+ "model.layers.16.conv.out_proj.biases": "model.safetensors",
167
+ "model.layers.16.conv.out_proj.scales": "model.safetensors",
168
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
169
+ "model.layers.16.feed_forward.w1.biases": "model.safetensors",
170
+ "model.layers.16.feed_forward.w1.scales": "model.safetensors",
171
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
172
+ "model.layers.16.feed_forward.w2.biases": "model.safetensors",
173
+ "model.layers.16.feed_forward.w2.scales": "model.safetensors",
174
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
175
+ "model.layers.16.feed_forward.w3.biases": "model.safetensors",
176
+ "model.layers.16.feed_forward.w3.scales": "model.safetensors",
177
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
178
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
179
+ "model.layers.16.operator_norm.weight": "model.safetensors",
180
+ "model.layers.17.feed_forward.w1.biases": "model.safetensors",
181
+ "model.layers.17.feed_forward.w1.scales": "model.safetensors",
182
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
183
+ "model.layers.17.feed_forward.w2.biases": "model.safetensors",
184
+ "model.layers.17.feed_forward.w2.scales": "model.safetensors",
185
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
186
+ "model.layers.17.feed_forward.w3.biases": "model.safetensors",
187
+ "model.layers.17.feed_forward.w3.scales": "model.safetensors",
188
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
189
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
190
+ "model.layers.17.operator_norm.weight": "model.safetensors",
191
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
192
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
193
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
194
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
195
+ "model.layers.17.self_attn.out_proj.biases": "model.safetensors",
196
+ "model.layers.17.self_attn.out_proj.scales": "model.safetensors",
197
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
198
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
199
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
200
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
201
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
202
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
203
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
204
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
205
+ "model.layers.18.conv.conv.weight": "model.safetensors",
206
+ "model.layers.18.conv.in_proj.biases": "model.safetensors",
207
+ "model.layers.18.conv.in_proj.scales": "model.safetensors",
208
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
209
+ "model.layers.18.conv.out_proj.biases": "model.safetensors",
210
+ "model.layers.18.conv.out_proj.scales": "model.safetensors",
211
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
212
+ "model.layers.18.feed_forward.w1.biases": "model.safetensors",
213
+ "model.layers.18.feed_forward.w1.scales": "model.safetensors",
214
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
215
+ "model.layers.18.feed_forward.w2.biases": "model.safetensors",
216
+ "model.layers.18.feed_forward.w2.scales": "model.safetensors",
217
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
218
+ "model.layers.18.feed_forward.w3.biases": "model.safetensors",
219
+ "model.layers.18.feed_forward.w3.scales": "model.safetensors",
220
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
221
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
222
+ "model.layers.18.operator_norm.weight": "model.safetensors",
223
+ "model.layers.19.conv.conv.weight": "model.safetensors",
224
+ "model.layers.19.conv.in_proj.biases": "model.safetensors",
225
+ "model.layers.19.conv.in_proj.scales": "model.safetensors",
226
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
227
+ "model.layers.19.conv.out_proj.biases": "model.safetensors",
228
+ "model.layers.19.conv.out_proj.scales": "model.safetensors",
229
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
230
+ "model.layers.19.feed_forward.w1.biases": "model.safetensors",
231
+ "model.layers.19.feed_forward.w1.scales": "model.safetensors",
232
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
233
+ "model.layers.19.feed_forward.w2.biases": "model.safetensors",
234
+ "model.layers.19.feed_forward.w2.scales": "model.safetensors",
235
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
236
+ "model.layers.19.feed_forward.w3.biases": "model.safetensors",
237
+ "model.layers.19.feed_forward.w3.scales": "model.safetensors",
238
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
239
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
240
+ "model.layers.19.operator_norm.weight": "model.safetensors",
241
+ "model.layers.2.feed_forward.w1.biases": "model.safetensors",
242
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
243
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
244
+ "model.layers.2.feed_forward.w2.biases": "model.safetensors",
245
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
246
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
247
+ "model.layers.2.feed_forward.w3.biases": "model.safetensors",
248
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
249
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
250
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
251
+ "model.layers.2.operator_norm.weight": "model.safetensors",
252
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
253
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
254
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
255
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
257
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
258
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
259
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
260
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
261
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
262
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
263
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
264
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
265
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
266
+ "model.layers.20.conv.conv.weight": "model.safetensors",
267
+ "model.layers.20.conv.in_proj.biases": "model.safetensors",
268
+ "model.layers.20.conv.in_proj.scales": "model.safetensors",
269
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
270
+ "model.layers.20.conv.out_proj.biases": "model.safetensors",
271
+ "model.layers.20.conv.out_proj.scales": "model.safetensors",
272
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
273
+ "model.layers.20.feed_forward.w1.biases": "model.safetensors",
274
+ "model.layers.20.feed_forward.w1.scales": "model.safetensors",
275
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
276
+ "model.layers.20.feed_forward.w2.biases": "model.safetensors",
277
+ "model.layers.20.feed_forward.w2.scales": "model.safetensors",
278
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
279
+ "model.layers.20.feed_forward.w3.biases": "model.safetensors",
280
+ "model.layers.20.feed_forward.w3.scales": "model.safetensors",
281
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
282
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
283
+ "model.layers.20.operator_norm.weight": "model.safetensors",
284
+ "model.layers.21.feed_forward.w1.biases": "model.safetensors",
285
+ "model.layers.21.feed_forward.w1.scales": "model.safetensors",
286
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
287
+ "model.layers.21.feed_forward.w2.biases": "model.safetensors",
288
+ "model.layers.21.feed_forward.w2.scales": "model.safetensors",
289
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
290
+ "model.layers.21.feed_forward.w3.biases": "model.safetensors",
291
+ "model.layers.21.feed_forward.w3.scales": "model.safetensors",
292
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
293
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
294
+ "model.layers.21.operator_norm.weight": "model.safetensors",
295
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
296
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
297
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
298
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
299
+ "model.layers.21.self_attn.out_proj.biases": "model.safetensors",
300
+ "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
301
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
302
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
303
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
304
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
305
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
306
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.22.conv.conv.weight": "model.safetensors",
310
+ "model.layers.22.conv.in_proj.biases": "model.safetensors",
311
+ "model.layers.22.conv.in_proj.scales": "model.safetensors",
312
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
313
+ "model.layers.22.conv.out_proj.biases": "model.safetensors",
314
+ "model.layers.22.conv.out_proj.scales": "model.safetensors",
315
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
316
+ "model.layers.22.feed_forward.w1.biases": "model.safetensors",
317
+ "model.layers.22.feed_forward.w1.scales": "model.safetensors",
318
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
319
+ "model.layers.22.feed_forward.w2.biases": "model.safetensors",
320
+ "model.layers.22.feed_forward.w2.scales": "model.safetensors",
321
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
322
+ "model.layers.22.feed_forward.w3.biases": "model.safetensors",
323
+ "model.layers.22.feed_forward.w3.scales": "model.safetensors",
324
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
325
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
326
+ "model.layers.22.operator_norm.weight": "model.safetensors",
327
+ "model.layers.23.conv.conv.weight": "model.safetensors",
328
+ "model.layers.23.conv.in_proj.biases": "model.safetensors",
329
+ "model.layers.23.conv.in_proj.scales": "model.safetensors",
330
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
331
+ "model.layers.23.conv.out_proj.biases": "model.safetensors",
332
+ "model.layers.23.conv.out_proj.scales": "model.safetensors",
333
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
334
+ "model.layers.23.feed_forward.w1.biases": "model.safetensors",
335
+ "model.layers.23.feed_forward.w1.scales": "model.safetensors",
336
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
337
+ "model.layers.23.feed_forward.w2.biases": "model.safetensors",
338
+ "model.layers.23.feed_forward.w2.scales": "model.safetensors",
339
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
340
+ "model.layers.23.feed_forward.w3.biases": "model.safetensors",
341
+ "model.layers.23.feed_forward.w3.scales": "model.safetensors",
342
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
343
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
344
+ "model.layers.23.operator_norm.weight": "model.safetensors",
345
+ "model.layers.24.feed_forward.w1.biases": "model.safetensors",
346
+ "model.layers.24.feed_forward.w1.scales": "model.safetensors",
347
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
348
+ "model.layers.24.feed_forward.w2.biases": "model.safetensors",
349
+ "model.layers.24.feed_forward.w2.scales": "model.safetensors",
350
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
351
+ "model.layers.24.feed_forward.w3.biases": "model.safetensors",
352
+ "model.layers.24.feed_forward.w3.scales": "model.safetensors",
353
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
354
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
355
+ "model.layers.24.operator_norm.weight": "model.safetensors",
356
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
357
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
358
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
359
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
360
+ "model.layers.24.self_attn.out_proj.biases": "model.safetensors",
361
+ "model.layers.24.self_attn.out_proj.scales": "model.safetensors",
362
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
363
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
364
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
365
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
366
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
367
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
368
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
369
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
370
+ "model.layers.25.conv.conv.weight": "model.safetensors",
371
+ "model.layers.25.conv.in_proj.biases": "model.safetensors",
372
+ "model.layers.25.conv.in_proj.scales": "model.safetensors",
373
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
374
+ "model.layers.25.conv.out_proj.biases": "model.safetensors",
375
+ "model.layers.25.conv.out_proj.scales": "model.safetensors",
376
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
377
+ "model.layers.25.feed_forward.w1.biases": "model.safetensors",
378
+ "model.layers.25.feed_forward.w1.scales": "model.safetensors",
379
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
380
+ "model.layers.25.feed_forward.w2.biases": "model.safetensors",
381
+ "model.layers.25.feed_forward.w2.scales": "model.safetensors",
382
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
383
+ "model.layers.25.feed_forward.w3.biases": "model.safetensors",
384
+ "model.layers.25.feed_forward.w3.scales": "model.safetensors",
385
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
386
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
387
+ "model.layers.25.operator_norm.weight": "model.safetensors",
388
+ "model.layers.26.conv.conv.weight": "model.safetensors",
389
+ "model.layers.26.conv.in_proj.biases": "model.safetensors",
390
+ "model.layers.26.conv.in_proj.scales": "model.safetensors",
391
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
392
+ "model.layers.26.conv.out_proj.biases": "model.safetensors",
393
+ "model.layers.26.conv.out_proj.scales": "model.safetensors",
394
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
395
+ "model.layers.26.feed_forward.w1.biases": "model.safetensors",
396
+ "model.layers.26.feed_forward.w1.scales": "model.safetensors",
397
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
398
+ "model.layers.26.feed_forward.w2.biases": "model.safetensors",
399
+ "model.layers.26.feed_forward.w2.scales": "model.safetensors",
400
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
401
+ "model.layers.26.feed_forward.w3.biases": "model.safetensors",
402
+ "model.layers.26.feed_forward.w3.scales": "model.safetensors",
403
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
404
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
405
+ "model.layers.26.operator_norm.weight": "model.safetensors",
406
+ "model.layers.27.feed_forward.w1.biases": "model.safetensors",
407
+ "model.layers.27.feed_forward.w1.scales": "model.safetensors",
408
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
409
+ "model.layers.27.feed_forward.w2.biases": "model.safetensors",
410
+ "model.layers.27.feed_forward.w2.scales": "model.safetensors",
411
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
412
+ "model.layers.27.feed_forward.w3.biases": "model.safetensors",
413
+ "model.layers.27.feed_forward.w3.scales": "model.safetensors",
414
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
415
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
416
+ "model.layers.27.operator_norm.weight": "model.safetensors",
417
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
418
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
419
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
420
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
421
+ "model.layers.27.self_attn.out_proj.biases": "model.safetensors",
422
+ "model.layers.27.self_attn.out_proj.scales": "model.safetensors",
423
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
424
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
425
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
426
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
427
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
428
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
429
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
430
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
431
+ "model.layers.28.conv.conv.weight": "model.safetensors",
432
+ "model.layers.28.conv.in_proj.biases": "model.safetensors",
433
+ "model.layers.28.conv.in_proj.scales": "model.safetensors",
434
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
435
+ "model.layers.28.conv.out_proj.biases": "model.safetensors",
436
+ "model.layers.28.conv.out_proj.scales": "model.safetensors",
437
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
438
+ "model.layers.28.feed_forward.w1.biases": "model.safetensors",
439
+ "model.layers.28.feed_forward.w1.scales": "model.safetensors",
440
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
441
+ "model.layers.28.feed_forward.w2.biases": "model.safetensors",
442
+ "model.layers.28.feed_forward.w2.scales": "model.safetensors",
443
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
444
+ "model.layers.28.feed_forward.w3.biases": "model.safetensors",
445
+ "model.layers.28.feed_forward.w3.scales": "model.safetensors",
446
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
447
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
448
+ "model.layers.28.operator_norm.weight": "model.safetensors",
449
+ "model.layers.29.conv.conv.weight": "model.safetensors",
450
+ "model.layers.29.conv.in_proj.biases": "model.safetensors",
451
+ "model.layers.29.conv.in_proj.scales": "model.safetensors",
452
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
453
+ "model.layers.29.conv.out_proj.biases": "model.safetensors",
454
+ "model.layers.29.conv.out_proj.scales": "model.safetensors",
455
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
456
+ "model.layers.29.feed_forward.w1.biases": "model.safetensors",
457
+ "model.layers.29.feed_forward.w1.scales": "model.safetensors",
458
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
459
+ "model.layers.29.feed_forward.w2.biases": "model.safetensors",
460
+ "model.layers.29.feed_forward.w2.scales": "model.safetensors",
461
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
462
+ "model.layers.29.feed_forward.w3.biases": "model.safetensors",
463
+ "model.layers.29.feed_forward.w3.scales": "model.safetensors",
464
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
465
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
466
+ "model.layers.29.operator_norm.weight": "model.safetensors",
467
+ "model.layers.3.conv.conv.weight": "model.safetensors",
468
+ "model.layers.3.conv.in_proj.biases": "model.safetensors",
469
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
470
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
471
+ "model.layers.3.conv.out_proj.biases": "model.safetensors",
472
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
473
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
474
+ "model.layers.3.feed_forward.w1.biases": "model.safetensors",
475
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
476
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
477
+ "model.layers.3.feed_forward.w2.biases": "model.safetensors",
478
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
479
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
480
+ "model.layers.3.feed_forward.w3.biases": "model.safetensors",
481
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
482
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
483
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
484
+ "model.layers.3.operator_norm.weight": "model.safetensors",
485
+ "model.layers.4.conv.conv.weight": "model.safetensors",
486
+ "model.layers.4.conv.in_proj.biases": "model.safetensors",
487
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
488
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
489
+ "model.layers.4.conv.out_proj.biases": "model.safetensors",
490
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
491
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
492
+ "model.layers.4.feed_forward.w1.biases": "model.safetensors",
493
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
494
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
495
+ "model.layers.4.feed_forward.w2.biases": "model.safetensors",
496
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
497
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
498
+ "model.layers.4.feed_forward.w3.biases": "model.safetensors",
499
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
500
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
501
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
502
+ "model.layers.4.operator_norm.weight": "model.safetensors",
503
+ "model.layers.5.feed_forward.w1.biases": "model.safetensors",
504
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
505
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
506
+ "model.layers.5.feed_forward.w2.biases": "model.safetensors",
507
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
508
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
509
+ "model.layers.5.feed_forward.w3.biases": "model.safetensors",
510
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
511
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
512
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
513
+ "model.layers.5.operator_norm.weight": "model.safetensors",
514
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
515
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
+ "model.layers.5.self_attn.out_proj.biases": "model.safetensors",
519
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
520
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
521
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
522
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
526
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
527
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
528
+ "model.layers.6.conv.conv.weight": "model.safetensors",
529
+ "model.layers.6.conv.in_proj.biases": "model.safetensors",
530
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
531
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
532
+ "model.layers.6.conv.out_proj.biases": "model.safetensors",
533
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
534
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
535
+ "model.layers.6.feed_forward.w1.biases": "model.safetensors",
536
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
537
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
538
+ "model.layers.6.feed_forward.w2.biases": "model.safetensors",
539
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
540
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
541
+ "model.layers.6.feed_forward.w3.biases": "model.safetensors",
542
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
543
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
544
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
545
+ "model.layers.6.operator_norm.weight": "model.safetensors",
546
+ "model.layers.7.conv.conv.weight": "model.safetensors",
547
+ "model.layers.7.conv.in_proj.biases": "model.safetensors",
548
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
549
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
550
+ "model.layers.7.conv.out_proj.biases": "model.safetensors",
551
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
552
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
553
+ "model.layers.7.feed_forward.w1.biases": "model.safetensors",
554
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
555
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
556
+ "model.layers.7.feed_forward.w2.biases": "model.safetensors",
557
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
558
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
559
+ "model.layers.7.feed_forward.w3.biases": "model.safetensors",
560
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
561
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
562
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
563
+ "model.layers.7.operator_norm.weight": "model.safetensors",
564
+ "model.layers.8.conv.conv.weight": "model.safetensors",
565
+ "model.layers.8.conv.in_proj.biases": "model.safetensors",
566
+ "model.layers.8.conv.in_proj.scales": "model.safetensors",
567
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
568
+ "model.layers.8.conv.out_proj.biases": "model.safetensors",
569
+ "model.layers.8.conv.out_proj.scales": "model.safetensors",
570
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
571
+ "model.layers.8.feed_forward.w1.biases": "model.safetensors",
572
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
573
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
574
+ "model.layers.8.feed_forward.w2.biases": "model.safetensors",
575
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
576
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
577
+ "model.layers.8.feed_forward.w3.biases": "model.safetensors",
578
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
579
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
580
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
581
+ "model.layers.8.operator_norm.weight": "model.safetensors",
582
+ "model.layers.9.feed_forward.w1.biases": "model.safetensors",
583
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
584
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
585
+ "model.layers.9.feed_forward.w2.biases": "model.safetensors",
586
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
587
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
588
+ "model.layers.9.feed_forward.w3.biases": "model.safetensors",
589
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
590
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
591
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
592
+ "model.layers.9.operator_norm.weight": "model.safetensors",
593
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
594
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
595
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
596
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
597
+ "model.layers.9.self_attn.out_proj.biases": "model.safetensors",
598
+ "model.layers.9.self_attn.out_proj.scales": "model.safetensors",
599
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
600
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
601
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
602
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
603
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
604
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
605
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
606
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
607
+ }
608
+ }
6bit/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
6bit/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
8bit/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
8bit/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 64,
69
+ "bits": 8,
70
+ "mode": "affine"
71
+ },
72
+ "quantization_config": {
73
+ "group_size": 64,
74
+ "bits": 8,
75
+ "mode": "affine"
76
+ },
77
+ "rope_parameters": {
78
+ "rope_theta": 10000000.0,
79
+ "rope_type": "default"
80
+ },
81
+ "rope_theta": 10000000.0,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.2.0",
84
+ "use_cache": true,
85
+ "use_pos_enc": true,
86
+ "vocab_size": 128000
87
+ }
8bit/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
8bit/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04f7c6997b1501ae2551109aee50d57419f651a80d1a68a58a2c4d53202ee1ca
3
+ size 2866086056
8bit/model.safetensors.index.json ADDED
@@ -0,0 +1,608 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2866018304,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model.safetensors",
8
+ "model.embed_tokens.scales": "model.safetensors",
9
+ "model.embed_tokens.weight": "model.safetensors",
10
+ "model.embedding_norm.weight": "model.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
18
+ "model.layers.0.feed_forward.w1.biases": "model.safetensors",
19
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
21
+ "model.layers.0.feed_forward.w2.biases": "model.safetensors",
22
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
23
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
24
+ "model.layers.0.feed_forward.w3.biases": "model.safetensors",
25
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
26
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
36
+ "model.layers.1.feed_forward.w1.biases": "model.safetensors",
37
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
38
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
39
+ "model.layers.1.feed_forward.w2.biases": "model.safetensors",
40
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
41
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
42
+ "model.layers.1.feed_forward.w3.biases": "model.safetensors",
43
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
44
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model.safetensors",
47
+ "model.layers.10.conv.conv.weight": "model.safetensors",
48
+ "model.layers.10.conv.in_proj.biases": "model.safetensors",
49
+ "model.layers.10.conv.in_proj.scales": "model.safetensors",
50
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
51
+ "model.layers.10.conv.out_proj.biases": "model.safetensors",
52
+ "model.layers.10.conv.out_proj.scales": "model.safetensors",
53
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
54
+ "model.layers.10.feed_forward.w1.biases": "model.safetensors",
55
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
56
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
57
+ "model.layers.10.feed_forward.w2.biases": "model.safetensors",
58
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
59
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
60
+ "model.layers.10.feed_forward.w3.biases": "model.safetensors",
61
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
62
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
63
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
64
+ "model.layers.10.operator_norm.weight": "model.safetensors",
65
+ "model.layers.11.conv.conv.weight": "model.safetensors",
66
+ "model.layers.11.conv.in_proj.biases": "model.safetensors",
67
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
68
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
69
+ "model.layers.11.conv.out_proj.biases": "model.safetensors",
70
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
71
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
72
+ "model.layers.11.feed_forward.w1.biases": "model.safetensors",
73
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
74
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
75
+ "model.layers.11.feed_forward.w2.biases": "model.safetensors",
76
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
77
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
78
+ "model.layers.11.feed_forward.w3.biases": "model.safetensors",
79
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
80
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
81
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
82
+ "model.layers.11.operator_norm.weight": "model.safetensors",
83
+ "model.layers.12.conv.conv.weight": "model.safetensors",
84
+ "model.layers.12.conv.in_proj.biases": "model.safetensors",
85
+ "model.layers.12.conv.in_proj.scales": "model.safetensors",
86
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
87
+ "model.layers.12.conv.out_proj.biases": "model.safetensors",
88
+ "model.layers.12.conv.out_proj.scales": "model.safetensors",
89
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
90
+ "model.layers.12.feed_forward.w1.biases": "model.safetensors",
91
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
92
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
93
+ "model.layers.12.feed_forward.w2.biases": "model.safetensors",
94
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
95
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
96
+ "model.layers.12.feed_forward.w3.biases": "model.safetensors",
97
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
98
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
99
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
100
+ "model.layers.12.operator_norm.weight": "model.safetensors",
101
+ "model.layers.13.feed_forward.w1.biases": "model.safetensors",
102
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
103
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
104
+ "model.layers.13.feed_forward.w2.biases": "model.safetensors",
105
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
106
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
107
+ "model.layers.13.feed_forward.w3.biases": "model.safetensors",
108
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
109
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
110
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
111
+ "model.layers.13.operator_norm.weight": "model.safetensors",
112
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
113
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
114
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
115
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
116
+ "model.layers.13.self_attn.out_proj.biases": "model.safetensors",
117
+ "model.layers.13.self_attn.out_proj.scales": "model.safetensors",
118
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
119
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
120
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
121
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
122
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
124
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
125
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
126
+ "model.layers.14.conv.conv.weight": "model.safetensors",
127
+ "model.layers.14.conv.in_proj.biases": "model.safetensors",
128
+ "model.layers.14.conv.in_proj.scales": "model.safetensors",
129
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
130
+ "model.layers.14.conv.out_proj.biases": "model.safetensors",
131
+ "model.layers.14.conv.out_proj.scales": "model.safetensors",
132
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
133
+ "model.layers.14.feed_forward.w1.biases": "model.safetensors",
134
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
135
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
136
+ "model.layers.14.feed_forward.w2.biases": "model.safetensors",
137
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
138
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
139
+ "model.layers.14.feed_forward.w3.biases": "model.safetensors",
140
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
141
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
142
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
143
+ "model.layers.14.operator_norm.weight": "model.safetensors",
144
+ "model.layers.15.conv.conv.weight": "model.safetensors",
145
+ "model.layers.15.conv.in_proj.biases": "model.safetensors",
146
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
147
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
148
+ "model.layers.15.conv.out_proj.biases": "model.safetensors",
149
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
150
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
151
+ "model.layers.15.feed_forward.w1.biases": "model.safetensors",
152
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
153
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
154
+ "model.layers.15.feed_forward.w2.biases": "model.safetensors",
155
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
156
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
157
+ "model.layers.15.feed_forward.w3.biases": "model.safetensors",
158
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
159
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
160
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
161
+ "model.layers.15.operator_norm.weight": "model.safetensors",
162
+ "model.layers.16.conv.conv.weight": "model.safetensors",
163
+ "model.layers.16.conv.in_proj.biases": "model.safetensors",
164
+ "model.layers.16.conv.in_proj.scales": "model.safetensors",
165
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
166
+ "model.layers.16.conv.out_proj.biases": "model.safetensors",
167
+ "model.layers.16.conv.out_proj.scales": "model.safetensors",
168
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
169
+ "model.layers.16.feed_forward.w1.biases": "model.safetensors",
170
+ "model.layers.16.feed_forward.w1.scales": "model.safetensors",
171
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
172
+ "model.layers.16.feed_forward.w2.biases": "model.safetensors",
173
+ "model.layers.16.feed_forward.w2.scales": "model.safetensors",
174
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
175
+ "model.layers.16.feed_forward.w3.biases": "model.safetensors",
176
+ "model.layers.16.feed_forward.w3.scales": "model.safetensors",
177
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
178
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
179
+ "model.layers.16.operator_norm.weight": "model.safetensors",
180
+ "model.layers.17.feed_forward.w1.biases": "model.safetensors",
181
+ "model.layers.17.feed_forward.w1.scales": "model.safetensors",
182
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
183
+ "model.layers.17.feed_forward.w2.biases": "model.safetensors",
184
+ "model.layers.17.feed_forward.w2.scales": "model.safetensors",
185
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
186
+ "model.layers.17.feed_forward.w3.biases": "model.safetensors",
187
+ "model.layers.17.feed_forward.w3.scales": "model.safetensors",
188
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
189
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
190
+ "model.layers.17.operator_norm.weight": "model.safetensors",
191
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
192
+ "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
193
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
194
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
195
+ "model.layers.17.self_attn.out_proj.biases": "model.safetensors",
196
+ "model.layers.17.self_attn.out_proj.scales": "model.safetensors",
197
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
198
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
199
+ "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
200
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
201
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
202
+ "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
203
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
204
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
205
+ "model.layers.18.conv.conv.weight": "model.safetensors",
206
+ "model.layers.18.conv.in_proj.biases": "model.safetensors",
207
+ "model.layers.18.conv.in_proj.scales": "model.safetensors",
208
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
209
+ "model.layers.18.conv.out_proj.biases": "model.safetensors",
210
+ "model.layers.18.conv.out_proj.scales": "model.safetensors",
211
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
212
+ "model.layers.18.feed_forward.w1.biases": "model.safetensors",
213
+ "model.layers.18.feed_forward.w1.scales": "model.safetensors",
214
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
215
+ "model.layers.18.feed_forward.w2.biases": "model.safetensors",
216
+ "model.layers.18.feed_forward.w2.scales": "model.safetensors",
217
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
218
+ "model.layers.18.feed_forward.w3.biases": "model.safetensors",
219
+ "model.layers.18.feed_forward.w3.scales": "model.safetensors",
220
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
221
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
222
+ "model.layers.18.operator_norm.weight": "model.safetensors",
223
+ "model.layers.19.conv.conv.weight": "model.safetensors",
224
+ "model.layers.19.conv.in_proj.biases": "model.safetensors",
225
+ "model.layers.19.conv.in_proj.scales": "model.safetensors",
226
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
227
+ "model.layers.19.conv.out_proj.biases": "model.safetensors",
228
+ "model.layers.19.conv.out_proj.scales": "model.safetensors",
229
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
230
+ "model.layers.19.feed_forward.w1.biases": "model.safetensors",
231
+ "model.layers.19.feed_forward.w1.scales": "model.safetensors",
232
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
233
+ "model.layers.19.feed_forward.w2.biases": "model.safetensors",
234
+ "model.layers.19.feed_forward.w2.scales": "model.safetensors",
235
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
236
+ "model.layers.19.feed_forward.w3.biases": "model.safetensors",
237
+ "model.layers.19.feed_forward.w3.scales": "model.safetensors",
238
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
239
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
240
+ "model.layers.19.operator_norm.weight": "model.safetensors",
241
+ "model.layers.2.feed_forward.w1.biases": "model.safetensors",
242
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
243
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
244
+ "model.layers.2.feed_forward.w2.biases": "model.safetensors",
245
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
246
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
247
+ "model.layers.2.feed_forward.w3.biases": "model.safetensors",
248
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
249
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
250
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
251
+ "model.layers.2.operator_norm.weight": "model.safetensors",
252
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
253
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
254
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
255
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
257
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
258
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
259
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
260
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
261
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
262
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
263
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
264
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
265
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
266
+ "model.layers.20.conv.conv.weight": "model.safetensors",
267
+ "model.layers.20.conv.in_proj.biases": "model.safetensors",
268
+ "model.layers.20.conv.in_proj.scales": "model.safetensors",
269
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
270
+ "model.layers.20.conv.out_proj.biases": "model.safetensors",
271
+ "model.layers.20.conv.out_proj.scales": "model.safetensors",
272
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
273
+ "model.layers.20.feed_forward.w1.biases": "model.safetensors",
274
+ "model.layers.20.feed_forward.w1.scales": "model.safetensors",
275
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
276
+ "model.layers.20.feed_forward.w2.biases": "model.safetensors",
277
+ "model.layers.20.feed_forward.w2.scales": "model.safetensors",
278
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
279
+ "model.layers.20.feed_forward.w3.biases": "model.safetensors",
280
+ "model.layers.20.feed_forward.w3.scales": "model.safetensors",
281
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
282
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
283
+ "model.layers.20.operator_norm.weight": "model.safetensors",
284
+ "model.layers.21.feed_forward.w1.biases": "model.safetensors",
285
+ "model.layers.21.feed_forward.w1.scales": "model.safetensors",
286
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
287
+ "model.layers.21.feed_forward.w2.biases": "model.safetensors",
288
+ "model.layers.21.feed_forward.w2.scales": "model.safetensors",
289
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
290
+ "model.layers.21.feed_forward.w3.biases": "model.safetensors",
291
+ "model.layers.21.feed_forward.w3.scales": "model.safetensors",
292
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
293
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
294
+ "model.layers.21.operator_norm.weight": "model.safetensors",
295
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
296
+ "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
297
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
298
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
299
+ "model.layers.21.self_attn.out_proj.biases": "model.safetensors",
300
+ "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
301
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
302
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
303
+ "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
304
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
305
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
306
+ "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
307
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
308
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
309
+ "model.layers.22.conv.conv.weight": "model.safetensors",
310
+ "model.layers.22.conv.in_proj.biases": "model.safetensors",
311
+ "model.layers.22.conv.in_proj.scales": "model.safetensors",
312
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
313
+ "model.layers.22.conv.out_proj.biases": "model.safetensors",
314
+ "model.layers.22.conv.out_proj.scales": "model.safetensors",
315
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
316
+ "model.layers.22.feed_forward.w1.biases": "model.safetensors",
317
+ "model.layers.22.feed_forward.w1.scales": "model.safetensors",
318
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
319
+ "model.layers.22.feed_forward.w2.biases": "model.safetensors",
320
+ "model.layers.22.feed_forward.w2.scales": "model.safetensors",
321
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
322
+ "model.layers.22.feed_forward.w3.biases": "model.safetensors",
323
+ "model.layers.22.feed_forward.w3.scales": "model.safetensors",
324
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
325
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
326
+ "model.layers.22.operator_norm.weight": "model.safetensors",
327
+ "model.layers.23.conv.conv.weight": "model.safetensors",
328
+ "model.layers.23.conv.in_proj.biases": "model.safetensors",
329
+ "model.layers.23.conv.in_proj.scales": "model.safetensors",
330
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
331
+ "model.layers.23.conv.out_proj.biases": "model.safetensors",
332
+ "model.layers.23.conv.out_proj.scales": "model.safetensors",
333
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
334
+ "model.layers.23.feed_forward.w1.biases": "model.safetensors",
335
+ "model.layers.23.feed_forward.w1.scales": "model.safetensors",
336
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
337
+ "model.layers.23.feed_forward.w2.biases": "model.safetensors",
338
+ "model.layers.23.feed_forward.w2.scales": "model.safetensors",
339
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
340
+ "model.layers.23.feed_forward.w3.biases": "model.safetensors",
341
+ "model.layers.23.feed_forward.w3.scales": "model.safetensors",
342
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
343
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
344
+ "model.layers.23.operator_norm.weight": "model.safetensors",
345
+ "model.layers.24.feed_forward.w1.biases": "model.safetensors",
346
+ "model.layers.24.feed_forward.w1.scales": "model.safetensors",
347
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
348
+ "model.layers.24.feed_forward.w2.biases": "model.safetensors",
349
+ "model.layers.24.feed_forward.w2.scales": "model.safetensors",
350
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
351
+ "model.layers.24.feed_forward.w3.biases": "model.safetensors",
352
+ "model.layers.24.feed_forward.w3.scales": "model.safetensors",
353
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
354
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
355
+ "model.layers.24.operator_norm.weight": "model.safetensors",
356
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
357
+ "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
358
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
359
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
360
+ "model.layers.24.self_attn.out_proj.biases": "model.safetensors",
361
+ "model.layers.24.self_attn.out_proj.scales": "model.safetensors",
362
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
363
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
364
+ "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
365
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
366
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
367
+ "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
368
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
369
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
370
+ "model.layers.25.conv.conv.weight": "model.safetensors",
371
+ "model.layers.25.conv.in_proj.biases": "model.safetensors",
372
+ "model.layers.25.conv.in_proj.scales": "model.safetensors",
373
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
374
+ "model.layers.25.conv.out_proj.biases": "model.safetensors",
375
+ "model.layers.25.conv.out_proj.scales": "model.safetensors",
376
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
377
+ "model.layers.25.feed_forward.w1.biases": "model.safetensors",
378
+ "model.layers.25.feed_forward.w1.scales": "model.safetensors",
379
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
380
+ "model.layers.25.feed_forward.w2.biases": "model.safetensors",
381
+ "model.layers.25.feed_forward.w2.scales": "model.safetensors",
382
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
383
+ "model.layers.25.feed_forward.w3.biases": "model.safetensors",
384
+ "model.layers.25.feed_forward.w3.scales": "model.safetensors",
385
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
386
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
387
+ "model.layers.25.operator_norm.weight": "model.safetensors",
388
+ "model.layers.26.conv.conv.weight": "model.safetensors",
389
+ "model.layers.26.conv.in_proj.biases": "model.safetensors",
390
+ "model.layers.26.conv.in_proj.scales": "model.safetensors",
391
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
392
+ "model.layers.26.conv.out_proj.biases": "model.safetensors",
393
+ "model.layers.26.conv.out_proj.scales": "model.safetensors",
394
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
395
+ "model.layers.26.feed_forward.w1.biases": "model.safetensors",
396
+ "model.layers.26.feed_forward.w1.scales": "model.safetensors",
397
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
398
+ "model.layers.26.feed_forward.w2.biases": "model.safetensors",
399
+ "model.layers.26.feed_forward.w2.scales": "model.safetensors",
400
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
401
+ "model.layers.26.feed_forward.w3.biases": "model.safetensors",
402
+ "model.layers.26.feed_forward.w3.scales": "model.safetensors",
403
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
404
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
405
+ "model.layers.26.operator_norm.weight": "model.safetensors",
406
+ "model.layers.27.feed_forward.w1.biases": "model.safetensors",
407
+ "model.layers.27.feed_forward.w1.scales": "model.safetensors",
408
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
409
+ "model.layers.27.feed_forward.w2.biases": "model.safetensors",
410
+ "model.layers.27.feed_forward.w2.scales": "model.safetensors",
411
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
412
+ "model.layers.27.feed_forward.w3.biases": "model.safetensors",
413
+ "model.layers.27.feed_forward.w3.scales": "model.safetensors",
414
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
415
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
416
+ "model.layers.27.operator_norm.weight": "model.safetensors",
417
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
418
+ "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
419
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
420
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
421
+ "model.layers.27.self_attn.out_proj.biases": "model.safetensors",
422
+ "model.layers.27.self_attn.out_proj.scales": "model.safetensors",
423
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
424
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
425
+ "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
426
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
427
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
428
+ "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
429
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
430
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
431
+ "model.layers.28.conv.conv.weight": "model.safetensors",
432
+ "model.layers.28.conv.in_proj.biases": "model.safetensors",
433
+ "model.layers.28.conv.in_proj.scales": "model.safetensors",
434
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
435
+ "model.layers.28.conv.out_proj.biases": "model.safetensors",
436
+ "model.layers.28.conv.out_proj.scales": "model.safetensors",
437
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
438
+ "model.layers.28.feed_forward.w1.biases": "model.safetensors",
439
+ "model.layers.28.feed_forward.w1.scales": "model.safetensors",
440
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
441
+ "model.layers.28.feed_forward.w2.biases": "model.safetensors",
442
+ "model.layers.28.feed_forward.w2.scales": "model.safetensors",
443
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
444
+ "model.layers.28.feed_forward.w3.biases": "model.safetensors",
445
+ "model.layers.28.feed_forward.w3.scales": "model.safetensors",
446
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
447
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
448
+ "model.layers.28.operator_norm.weight": "model.safetensors",
449
+ "model.layers.29.conv.conv.weight": "model.safetensors",
450
+ "model.layers.29.conv.in_proj.biases": "model.safetensors",
451
+ "model.layers.29.conv.in_proj.scales": "model.safetensors",
452
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
453
+ "model.layers.29.conv.out_proj.biases": "model.safetensors",
454
+ "model.layers.29.conv.out_proj.scales": "model.safetensors",
455
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
456
+ "model.layers.29.feed_forward.w1.biases": "model.safetensors",
457
+ "model.layers.29.feed_forward.w1.scales": "model.safetensors",
458
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
459
+ "model.layers.29.feed_forward.w2.biases": "model.safetensors",
460
+ "model.layers.29.feed_forward.w2.scales": "model.safetensors",
461
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
462
+ "model.layers.29.feed_forward.w3.biases": "model.safetensors",
463
+ "model.layers.29.feed_forward.w3.scales": "model.safetensors",
464
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
465
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
466
+ "model.layers.29.operator_norm.weight": "model.safetensors",
467
+ "model.layers.3.conv.conv.weight": "model.safetensors",
468
+ "model.layers.3.conv.in_proj.biases": "model.safetensors",
469
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
470
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
471
+ "model.layers.3.conv.out_proj.biases": "model.safetensors",
472
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
473
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
474
+ "model.layers.3.feed_forward.w1.biases": "model.safetensors",
475
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
476
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
477
+ "model.layers.3.feed_forward.w2.biases": "model.safetensors",
478
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
479
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
480
+ "model.layers.3.feed_forward.w3.biases": "model.safetensors",
481
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
482
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
483
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
484
+ "model.layers.3.operator_norm.weight": "model.safetensors",
485
+ "model.layers.4.conv.conv.weight": "model.safetensors",
486
+ "model.layers.4.conv.in_proj.biases": "model.safetensors",
487
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
488
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
489
+ "model.layers.4.conv.out_proj.biases": "model.safetensors",
490
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
491
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
492
+ "model.layers.4.feed_forward.w1.biases": "model.safetensors",
493
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
494
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
495
+ "model.layers.4.feed_forward.w2.biases": "model.safetensors",
496
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
497
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
498
+ "model.layers.4.feed_forward.w3.biases": "model.safetensors",
499
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
500
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
501
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
502
+ "model.layers.4.operator_norm.weight": "model.safetensors",
503
+ "model.layers.5.feed_forward.w1.biases": "model.safetensors",
504
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
505
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
506
+ "model.layers.5.feed_forward.w2.biases": "model.safetensors",
507
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
508
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
509
+ "model.layers.5.feed_forward.w3.biases": "model.safetensors",
510
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
511
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
512
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
513
+ "model.layers.5.operator_norm.weight": "model.safetensors",
514
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
515
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
516
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
517
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
518
+ "model.layers.5.self_attn.out_proj.biases": "model.safetensors",
519
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
520
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
521
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
522
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
523
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
524
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
525
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
526
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
527
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
528
+ "model.layers.6.conv.conv.weight": "model.safetensors",
529
+ "model.layers.6.conv.in_proj.biases": "model.safetensors",
530
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
531
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
532
+ "model.layers.6.conv.out_proj.biases": "model.safetensors",
533
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
534
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
535
+ "model.layers.6.feed_forward.w1.biases": "model.safetensors",
536
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
537
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
538
+ "model.layers.6.feed_forward.w2.biases": "model.safetensors",
539
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
540
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
541
+ "model.layers.6.feed_forward.w3.biases": "model.safetensors",
542
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
543
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
544
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
545
+ "model.layers.6.operator_norm.weight": "model.safetensors",
546
+ "model.layers.7.conv.conv.weight": "model.safetensors",
547
+ "model.layers.7.conv.in_proj.biases": "model.safetensors",
548
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
549
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
550
+ "model.layers.7.conv.out_proj.biases": "model.safetensors",
551
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
552
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
553
+ "model.layers.7.feed_forward.w1.biases": "model.safetensors",
554
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
555
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
556
+ "model.layers.7.feed_forward.w2.biases": "model.safetensors",
557
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
558
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
559
+ "model.layers.7.feed_forward.w3.biases": "model.safetensors",
560
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
561
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
562
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
563
+ "model.layers.7.operator_norm.weight": "model.safetensors",
564
+ "model.layers.8.conv.conv.weight": "model.safetensors",
565
+ "model.layers.8.conv.in_proj.biases": "model.safetensors",
566
+ "model.layers.8.conv.in_proj.scales": "model.safetensors",
567
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
568
+ "model.layers.8.conv.out_proj.biases": "model.safetensors",
569
+ "model.layers.8.conv.out_proj.scales": "model.safetensors",
570
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
571
+ "model.layers.8.feed_forward.w1.biases": "model.safetensors",
572
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
573
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
574
+ "model.layers.8.feed_forward.w2.biases": "model.safetensors",
575
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
576
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
577
+ "model.layers.8.feed_forward.w3.biases": "model.safetensors",
578
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
579
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
580
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
581
+ "model.layers.8.operator_norm.weight": "model.safetensors",
582
+ "model.layers.9.feed_forward.w1.biases": "model.safetensors",
583
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
584
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
585
+ "model.layers.9.feed_forward.w2.biases": "model.safetensors",
586
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
587
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
588
+ "model.layers.9.feed_forward.w3.biases": "model.safetensors",
589
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
590
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
591
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
592
+ "model.layers.9.operator_norm.weight": "model.safetensors",
593
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
594
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
595
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
596
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
597
+ "model.layers.9.self_attn.out_proj.biases": "model.safetensors",
598
+ "model.layers.9.self_attn.out_proj.scales": "model.safetensors",
599
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
600
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
601
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
602
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
603
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
604
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
605
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
606
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
607
+ }
608
+ }
8bit/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
8bit/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
LICENSE ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LFM Open License v1.0
2
+
3
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
4
+
5
+ 1. Definitions.
6
+
7
+ "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by this document.
8
+
9
+ "Licensor" shall mean Liquid AI, Inc.
10
+
11
+ "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
12
+
13
+ "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
14
+
15
+ "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
16
+
17
+ "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
18
+
19
+ "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work.
20
+
21
+ "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
22
+
23
+ "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
24
+
25
+ "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
26
+
27
+ "Commercial Use" shall mean any use of the Work for direct or indirect commercial advantage or monetary compensation.
28
+
29
+ "Qualified Non-Profit Organization" shall mean a Legal Entity that is organized and operated exclusively for religious, charitable, scientific, testing for public safety, literary, or educational purposes, and which is exempt from federal income tax under Section 501(c)(3) of the United States Internal Revenue Code of 1986, as amended, or any equivalent non-profit or charitable organization in a foreign jurisdiction.
30
+
31
+ "Non-Commercial or Research Purposes" shall mean purposes that do not involve any use of the Work or a Derivative Work for Commercial Use.
32
+
33
+ "Threshold" shall mean annual revenue of 10 million United States dollars ($10,000,000) or more.
34
+
35
+ 2. Grant of Copyright License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
36
+
37
+ 3. Grant of Patent License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
38
+
39
+ 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
40
+
41
+ (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
42
+
43
+ (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
44
+
45
+ (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
46
+
47
+ (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
48
+
49
+ You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
50
+
51
+ 5. Commercial Use Limitation.
52
+
53
+ (a) The rights granted under this License for Commercial Use are conditioned upon You or Your Legal Entity not exceeding the Threshold.
54
+
55
+ (b) Any Commercial Use of the Work or a Derivative Work by a Legal Entity that exceeds the Threshold is not licensed under this Agreement.
56
+
57
+ (c) The Threshold shall not apply to a Qualified Non-Profit Organization's use of the Work or a Derivative Work for Non-Commercial or Research Purposes.
58
+
59
+ 6. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
60
+
61
+ 7. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except for the reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
62
+
63
+ 8. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
64
+
65
+ 9. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
66
+
67
+ 10. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
68
+
69
+ 11. Termination. This License will terminate automatically and immediately if You fail to comply with any of its terms and conditions. Upon termination, You must cease all use of the Work and any Derivative Works and delete all copies in Your possession.
70
+
71
+ END OF TERMS AND CONDITIONS
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ license: other
4
+ license_name: lfm1.0
5
+ license_link: LICENSE
6
+ language:
7
+ - ar
8
+ - zh
9
+ - en
10
+ - fr
11
+ - de
12
+ - hi
13
+ - id
14
+ - it
15
+ - ja
16
+ - ko
17
+ - pl
18
+ - pt
19
+ - ru
20
+ - es
21
+ - th
22
+ - vi
23
+ pipeline_tag: text-generation
24
+ tags:
25
+ - liquid
26
+ - lfm2.5
27
+ - edge
28
+ - mlx
29
+ base_model: LiquidAI/LFM2.5-2.6B
30
+ ---
31
+
32
+ <div align="center">
33
+ <img
34
+ src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png"
35
+ alt="Liquid AI"
36
+ style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
37
+ />
38
+ <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
39
+ <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> &bull;
40
+ <a href="https://docs.liquid.ai/lfm/getting-started/welcome"><strong>Docs</strong></a> &bull;
41
+ <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> &bull;
42
+ <a href="https://discord.com/invite/liquid-ai"><strong>Discord</strong></a>
43
+ </div>
44
+ </div>
45
+
46
+ # LFM2.5-2.6B-MLX
47
+
48
+ LFM2.5 is a new family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
49
+
50
+ Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-2.6B
51
+
52
+ ## Precisions
53
+
54
+ | Folder | Precision | Group Size | Size |
55
+ |--------|-----------|------------|------|
56
+ | [`bf16/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/bf16) | bf16 | - | 5.02 GB |
57
+ | [`8bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/8bit) | 8-bit | 64 | 2.67 GB |
58
+ | [`6bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/6bit) | 6-bit | 64 | 2.04 GB |
59
+ | [`5bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/5bit) | 5-bit | 64 | 1.76 GB |
60
+ | [`4bit/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/4bit) | 4-bit | 64 | 1.47 GB |
61
+ | [`mxfp8/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/mxfp8) | MXFP8 | 32 | 2.59 GB |
62
+ | [`mxfp4/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/mxfp4) | MXFP4 | 32 | 1.46 GB |
63
+ | [`nvfp4/`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-MLX/tree/main/nvfp4) | NVFP4 | 16 | 1.53 GB |
64
+
65
+ ## Use with mlx
66
+
67
+ `mlx_lm.load` does not resolve subfolders of a HuggingFace repo directly (ml-explore/mlx-lm#403), so download the precision you want first:
68
+
69
+ ```bash
70
+ pip install mlx-lm
71
+ ```
72
+
73
+ ```python
74
+ from huggingface_hub import snapshot_download
75
+ from mlx_lm import load, generate
76
+ from mlx_lm.sample_utils import make_sampler
77
+
78
+ path = snapshot_download("LiquidAI/LFM2.5-2.6B-MLX", allow_patterns=["4bit/*"])
79
+ model, tokenizer = load(f"{path}/4bit")
80
+
81
+ response = generate(
82
+ model,
83
+ tokenizer,
84
+ prompt="The capital of France is",
85
+ max_tokens=100,
86
+ sampler=make_sampler(temp=0.7),
87
+ verbose=True,
88
+ )
89
+ ```
bf16/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
bf16/config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "rope_parameters": {
68
+ "rope_theta": 10000000.0,
69
+ "rope_type": "default"
70
+ },
71
+ "rope_theta": 10000000.0,
72
+ "tie_word_embeddings": true,
73
+ "transformers_version": "5.2.0",
74
+ "use_cache": true,
75
+ "use_pos_enc": true,
76
+ "vocab_size": 128000
77
+ }
bf16/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
bf16/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9fbb3bcdc165d0cc071c9b7b3b5e82ca9d6eb15826de4febf16079e43438061
3
+ size 5350374478
bf16/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55abdfa3fdd285d764910515ae176796d7bbe2c9302e19ce280c14a98f2362d4
3
+ size 44052910
bf16/model.safetensors.index.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5394397184,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.embedding_norm.weight": "model-00002-of-00002.safetensors",
9
+ "model.layers.0.conv.conv.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.conv.in_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.conv.out_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.operator_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.conv.conv.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.conv.in_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.conv.out_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.operator_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.conv.conv.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.conv.in_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.conv.out_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.operator_norm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.11.conv.conv.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.conv.in_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.conv.out_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.operator_norm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.12.conv.conv.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.12.conv.in_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.conv.out_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.operator_norm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.13.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.13.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.operator_norm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.14.conv.conv.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.conv.in_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.conv.out_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.operator_norm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.15.conv.conv.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.15.conv.in_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.conv.out_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.operator_norm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.16.conv.conv.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.16.conv.in_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.16.conv.out_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.operator_norm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.17.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.17.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.operator_norm.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.18.conv.conv.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.18.conv.in_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18.conv.out_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.operator_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.19.conv.conv.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.19.conv.in_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.19.conv.out_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.operator_norm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2.operator_norm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.20.conv.conv.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.20.conv.in_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20.conv.out_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.operator_norm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.21.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.21.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.operator_norm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.22.conv.conv.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.22.conv.in_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.conv.out_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.operator_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.23.conv.conv.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.23.conv.in_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.23.conv.out_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.operator_norm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.24.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.24.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.24.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.24.ffn_norm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.operator_norm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.25.conv.conv.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.25.conv.in_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.conv.out_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.ffn_norm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.operator_norm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.26.conv.conv.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.26.conv.in_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.26.conv.out_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.ffn_norm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.operator_norm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.27.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.27.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.27.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.27.ffn_norm.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.operator_norm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.28.conv.conv.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.28.conv.in_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.conv.out_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.ffn_norm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.operator_norm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.29.conv.conv.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.29.conv.in_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.29.conv.out_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.29.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.29.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.29.ffn_norm.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.operator_norm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.3.conv.conv.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.3.conv.in_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.3.conv.out_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.operator_norm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.4.conv.conv.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.4.conv.in_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.4.conv.out_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.4.operator_norm.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.5.operator_norm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.5.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.5.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.6.conv.conv.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.6.conv.in_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.6.conv.out_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.6.operator_norm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.7.conv.conv.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.7.conv.in_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.7.conv.out_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.7.operator_norm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.8.conv.conv.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.8.conv.in_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.8.conv.out_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.8.operator_norm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.9.operator_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.9.self_attn.k_layernorm.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.9.self_attn.q_layernorm.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
273
+ }
274
+ }
bf16/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
bf16/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
mxfp4/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
mxfp4/config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 32,
69
+ "bits": 4,
70
+ "mode": "mxfp4",
71
+ "model.embed_tokens": {
72
+ "group_size": 32,
73
+ "bits": 8,
74
+ "mode": "mxfp8"
75
+ }
76
+ },
77
+ "quantization_config": {
78
+ "group_size": 32,
79
+ "bits": 4,
80
+ "mode": "mxfp4",
81
+ "model.embed_tokens": {
82
+ "group_size": 32,
83
+ "bits": 8,
84
+ "mode": "mxfp8"
85
+ }
86
+ },
87
+ "rope_parameters": {
88
+ "rope_theta": 10000000.0,
89
+ "rope_type": "default"
90
+ },
91
+ "rope_theta": 10000000.0,
92
+ "tie_word_embeddings": true,
93
+ "transformers_version": "5.2.0",
94
+ "use_cache": true,
95
+ "use_pos_enc": true,
96
+ "vocab_size": 128000
97
+ }
mxfp4/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
mxfp4/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa9903442d924575ecd07f38766120f013a13ce5048633bdb6c3168baa961d3
3
+ size 1564390336
mxfp4/model.safetensors.index.json ADDED
@@ -0,0 +1,441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1564342272,
4
+ "total_parameters": 2697198592
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.scales": "model.safetensors",
8
+ "model.embed_tokens.weight": "model.safetensors",
9
+ "model.embedding_norm.weight": "model.safetensors",
10
+ "model.layers.0.conv.conv.weight": "model.safetensors",
11
+ "model.layers.0.conv.in_proj.scales": "model.safetensors",
12
+ "model.layers.0.conv.in_proj.weight": "model.safetensors",
13
+ "model.layers.0.conv.out_proj.scales": "model.safetensors",
14
+ "model.layers.0.conv.out_proj.weight": "model.safetensors",
15
+ "model.layers.0.feed_forward.w1.scales": "model.safetensors",
16
+ "model.layers.0.feed_forward.w1.weight": "model.safetensors",
17
+ "model.layers.0.feed_forward.w2.scales": "model.safetensors",
18
+ "model.layers.0.feed_forward.w2.weight": "model.safetensors",
19
+ "model.layers.0.feed_forward.w3.scales": "model.safetensors",
20
+ "model.layers.0.feed_forward.w3.weight": "model.safetensors",
21
+ "model.layers.0.ffn_norm.weight": "model.safetensors",
22
+ "model.layers.0.operator_norm.weight": "model.safetensors",
23
+ "model.layers.1.conv.conv.weight": "model.safetensors",
24
+ "model.layers.1.conv.in_proj.scales": "model.safetensors",
25
+ "model.layers.1.conv.in_proj.weight": "model.safetensors",
26
+ "model.layers.1.conv.out_proj.scales": "model.safetensors",
27
+ "model.layers.1.conv.out_proj.weight": "model.safetensors",
28
+ "model.layers.1.feed_forward.w1.scales": "model.safetensors",
29
+ "model.layers.1.feed_forward.w1.weight": "model.safetensors",
30
+ "model.layers.1.feed_forward.w2.scales": "model.safetensors",
31
+ "model.layers.1.feed_forward.w2.weight": "model.safetensors",
32
+ "model.layers.1.feed_forward.w3.scales": "model.safetensors",
33
+ "model.layers.1.feed_forward.w3.weight": "model.safetensors",
34
+ "model.layers.1.ffn_norm.weight": "model.safetensors",
35
+ "model.layers.1.operator_norm.weight": "model.safetensors",
36
+ "model.layers.10.conv.conv.weight": "model.safetensors",
37
+ "model.layers.10.conv.in_proj.scales": "model.safetensors",
38
+ "model.layers.10.conv.in_proj.weight": "model.safetensors",
39
+ "model.layers.10.conv.out_proj.scales": "model.safetensors",
40
+ "model.layers.10.conv.out_proj.weight": "model.safetensors",
41
+ "model.layers.10.feed_forward.w1.scales": "model.safetensors",
42
+ "model.layers.10.feed_forward.w1.weight": "model.safetensors",
43
+ "model.layers.10.feed_forward.w2.scales": "model.safetensors",
44
+ "model.layers.10.feed_forward.w2.weight": "model.safetensors",
45
+ "model.layers.10.feed_forward.w3.scales": "model.safetensors",
46
+ "model.layers.10.feed_forward.w3.weight": "model.safetensors",
47
+ "model.layers.10.ffn_norm.weight": "model.safetensors",
48
+ "model.layers.10.operator_norm.weight": "model.safetensors",
49
+ "model.layers.11.conv.conv.weight": "model.safetensors",
50
+ "model.layers.11.conv.in_proj.scales": "model.safetensors",
51
+ "model.layers.11.conv.in_proj.weight": "model.safetensors",
52
+ "model.layers.11.conv.out_proj.scales": "model.safetensors",
53
+ "model.layers.11.conv.out_proj.weight": "model.safetensors",
54
+ "model.layers.11.feed_forward.w1.scales": "model.safetensors",
55
+ "model.layers.11.feed_forward.w1.weight": "model.safetensors",
56
+ "model.layers.11.feed_forward.w2.scales": "model.safetensors",
57
+ "model.layers.11.feed_forward.w2.weight": "model.safetensors",
58
+ "model.layers.11.feed_forward.w3.scales": "model.safetensors",
59
+ "model.layers.11.feed_forward.w3.weight": "model.safetensors",
60
+ "model.layers.11.ffn_norm.weight": "model.safetensors",
61
+ "model.layers.11.operator_norm.weight": "model.safetensors",
62
+ "model.layers.12.conv.conv.weight": "model.safetensors",
63
+ "model.layers.12.conv.in_proj.scales": "model.safetensors",
64
+ "model.layers.12.conv.in_proj.weight": "model.safetensors",
65
+ "model.layers.12.conv.out_proj.scales": "model.safetensors",
66
+ "model.layers.12.conv.out_proj.weight": "model.safetensors",
67
+ "model.layers.12.feed_forward.w1.scales": "model.safetensors",
68
+ "model.layers.12.feed_forward.w1.weight": "model.safetensors",
69
+ "model.layers.12.feed_forward.w2.scales": "model.safetensors",
70
+ "model.layers.12.feed_forward.w2.weight": "model.safetensors",
71
+ "model.layers.12.feed_forward.w3.scales": "model.safetensors",
72
+ "model.layers.12.feed_forward.w3.weight": "model.safetensors",
73
+ "model.layers.12.ffn_norm.weight": "model.safetensors",
74
+ "model.layers.12.operator_norm.weight": "model.safetensors",
75
+ "model.layers.13.feed_forward.w1.scales": "model.safetensors",
76
+ "model.layers.13.feed_forward.w1.weight": "model.safetensors",
77
+ "model.layers.13.feed_forward.w2.scales": "model.safetensors",
78
+ "model.layers.13.feed_forward.w2.weight": "model.safetensors",
79
+ "model.layers.13.feed_forward.w3.scales": "model.safetensors",
80
+ "model.layers.13.feed_forward.w3.weight": "model.safetensors",
81
+ "model.layers.13.ffn_norm.weight": "model.safetensors",
82
+ "model.layers.13.operator_norm.weight": "model.safetensors",
83
+ "model.layers.13.self_attn.k_layernorm.weight": "model.safetensors",
84
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
85
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
86
+ "model.layers.13.self_attn.out_proj.scales": "model.safetensors",
87
+ "model.layers.13.self_attn.out_proj.weight": "model.safetensors",
88
+ "model.layers.13.self_attn.q_layernorm.weight": "model.safetensors",
89
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
90
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
91
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
92
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
93
+ "model.layers.14.conv.conv.weight": "model.safetensors",
94
+ "model.layers.14.conv.in_proj.scales": "model.safetensors",
95
+ "model.layers.14.conv.in_proj.weight": "model.safetensors",
96
+ "model.layers.14.conv.out_proj.scales": "model.safetensors",
97
+ "model.layers.14.conv.out_proj.weight": "model.safetensors",
98
+ "model.layers.14.feed_forward.w1.scales": "model.safetensors",
99
+ "model.layers.14.feed_forward.w1.weight": "model.safetensors",
100
+ "model.layers.14.feed_forward.w2.scales": "model.safetensors",
101
+ "model.layers.14.feed_forward.w2.weight": "model.safetensors",
102
+ "model.layers.14.feed_forward.w3.scales": "model.safetensors",
103
+ "model.layers.14.feed_forward.w3.weight": "model.safetensors",
104
+ "model.layers.14.ffn_norm.weight": "model.safetensors",
105
+ "model.layers.14.operator_norm.weight": "model.safetensors",
106
+ "model.layers.15.conv.conv.weight": "model.safetensors",
107
+ "model.layers.15.conv.in_proj.scales": "model.safetensors",
108
+ "model.layers.15.conv.in_proj.weight": "model.safetensors",
109
+ "model.layers.15.conv.out_proj.scales": "model.safetensors",
110
+ "model.layers.15.conv.out_proj.weight": "model.safetensors",
111
+ "model.layers.15.feed_forward.w1.scales": "model.safetensors",
112
+ "model.layers.15.feed_forward.w1.weight": "model.safetensors",
113
+ "model.layers.15.feed_forward.w2.scales": "model.safetensors",
114
+ "model.layers.15.feed_forward.w2.weight": "model.safetensors",
115
+ "model.layers.15.feed_forward.w3.scales": "model.safetensors",
116
+ "model.layers.15.feed_forward.w3.weight": "model.safetensors",
117
+ "model.layers.15.ffn_norm.weight": "model.safetensors",
118
+ "model.layers.15.operator_norm.weight": "model.safetensors",
119
+ "model.layers.16.conv.conv.weight": "model.safetensors",
120
+ "model.layers.16.conv.in_proj.scales": "model.safetensors",
121
+ "model.layers.16.conv.in_proj.weight": "model.safetensors",
122
+ "model.layers.16.conv.out_proj.scales": "model.safetensors",
123
+ "model.layers.16.conv.out_proj.weight": "model.safetensors",
124
+ "model.layers.16.feed_forward.w1.scales": "model.safetensors",
125
+ "model.layers.16.feed_forward.w1.weight": "model.safetensors",
126
+ "model.layers.16.feed_forward.w2.scales": "model.safetensors",
127
+ "model.layers.16.feed_forward.w2.weight": "model.safetensors",
128
+ "model.layers.16.feed_forward.w3.scales": "model.safetensors",
129
+ "model.layers.16.feed_forward.w3.weight": "model.safetensors",
130
+ "model.layers.16.ffn_norm.weight": "model.safetensors",
131
+ "model.layers.16.operator_norm.weight": "model.safetensors",
132
+ "model.layers.17.feed_forward.w1.scales": "model.safetensors",
133
+ "model.layers.17.feed_forward.w1.weight": "model.safetensors",
134
+ "model.layers.17.feed_forward.w2.scales": "model.safetensors",
135
+ "model.layers.17.feed_forward.w2.weight": "model.safetensors",
136
+ "model.layers.17.feed_forward.w3.scales": "model.safetensors",
137
+ "model.layers.17.feed_forward.w3.weight": "model.safetensors",
138
+ "model.layers.17.ffn_norm.weight": "model.safetensors",
139
+ "model.layers.17.operator_norm.weight": "model.safetensors",
140
+ "model.layers.17.self_attn.k_layernorm.weight": "model.safetensors",
141
+ "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
142
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
143
+ "model.layers.17.self_attn.out_proj.scales": "model.safetensors",
144
+ "model.layers.17.self_attn.out_proj.weight": "model.safetensors",
145
+ "model.layers.17.self_attn.q_layernorm.weight": "model.safetensors",
146
+ "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
147
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
148
+ "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
149
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
150
+ "model.layers.18.conv.conv.weight": "model.safetensors",
151
+ "model.layers.18.conv.in_proj.scales": "model.safetensors",
152
+ "model.layers.18.conv.in_proj.weight": "model.safetensors",
153
+ "model.layers.18.conv.out_proj.scales": "model.safetensors",
154
+ "model.layers.18.conv.out_proj.weight": "model.safetensors",
155
+ "model.layers.18.feed_forward.w1.scales": "model.safetensors",
156
+ "model.layers.18.feed_forward.w1.weight": "model.safetensors",
157
+ "model.layers.18.feed_forward.w2.scales": "model.safetensors",
158
+ "model.layers.18.feed_forward.w2.weight": "model.safetensors",
159
+ "model.layers.18.feed_forward.w3.scales": "model.safetensors",
160
+ "model.layers.18.feed_forward.w3.weight": "model.safetensors",
161
+ "model.layers.18.ffn_norm.weight": "model.safetensors",
162
+ "model.layers.18.operator_norm.weight": "model.safetensors",
163
+ "model.layers.19.conv.conv.weight": "model.safetensors",
164
+ "model.layers.19.conv.in_proj.scales": "model.safetensors",
165
+ "model.layers.19.conv.in_proj.weight": "model.safetensors",
166
+ "model.layers.19.conv.out_proj.scales": "model.safetensors",
167
+ "model.layers.19.conv.out_proj.weight": "model.safetensors",
168
+ "model.layers.19.feed_forward.w1.scales": "model.safetensors",
169
+ "model.layers.19.feed_forward.w1.weight": "model.safetensors",
170
+ "model.layers.19.feed_forward.w2.scales": "model.safetensors",
171
+ "model.layers.19.feed_forward.w2.weight": "model.safetensors",
172
+ "model.layers.19.feed_forward.w3.scales": "model.safetensors",
173
+ "model.layers.19.feed_forward.w3.weight": "model.safetensors",
174
+ "model.layers.19.ffn_norm.weight": "model.safetensors",
175
+ "model.layers.19.operator_norm.weight": "model.safetensors",
176
+ "model.layers.2.feed_forward.w1.scales": "model.safetensors",
177
+ "model.layers.2.feed_forward.w1.weight": "model.safetensors",
178
+ "model.layers.2.feed_forward.w2.scales": "model.safetensors",
179
+ "model.layers.2.feed_forward.w2.weight": "model.safetensors",
180
+ "model.layers.2.feed_forward.w3.scales": "model.safetensors",
181
+ "model.layers.2.feed_forward.w3.weight": "model.safetensors",
182
+ "model.layers.2.ffn_norm.weight": "model.safetensors",
183
+ "model.layers.2.operator_norm.weight": "model.safetensors",
184
+ "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
185
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
186
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
187
+ "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
188
+ "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
189
+ "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
190
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
191
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
192
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
193
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
194
+ "model.layers.20.conv.conv.weight": "model.safetensors",
195
+ "model.layers.20.conv.in_proj.scales": "model.safetensors",
196
+ "model.layers.20.conv.in_proj.weight": "model.safetensors",
197
+ "model.layers.20.conv.out_proj.scales": "model.safetensors",
198
+ "model.layers.20.conv.out_proj.weight": "model.safetensors",
199
+ "model.layers.20.feed_forward.w1.scales": "model.safetensors",
200
+ "model.layers.20.feed_forward.w1.weight": "model.safetensors",
201
+ "model.layers.20.feed_forward.w2.scales": "model.safetensors",
202
+ "model.layers.20.feed_forward.w2.weight": "model.safetensors",
203
+ "model.layers.20.feed_forward.w3.scales": "model.safetensors",
204
+ "model.layers.20.feed_forward.w3.weight": "model.safetensors",
205
+ "model.layers.20.ffn_norm.weight": "model.safetensors",
206
+ "model.layers.20.operator_norm.weight": "model.safetensors",
207
+ "model.layers.21.feed_forward.w1.scales": "model.safetensors",
208
+ "model.layers.21.feed_forward.w1.weight": "model.safetensors",
209
+ "model.layers.21.feed_forward.w2.scales": "model.safetensors",
210
+ "model.layers.21.feed_forward.w2.weight": "model.safetensors",
211
+ "model.layers.21.feed_forward.w3.scales": "model.safetensors",
212
+ "model.layers.21.feed_forward.w3.weight": "model.safetensors",
213
+ "model.layers.21.ffn_norm.weight": "model.safetensors",
214
+ "model.layers.21.operator_norm.weight": "model.safetensors",
215
+ "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
216
+ "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
217
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
218
+ "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
219
+ "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
220
+ "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
221
+ "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
222
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
223
+ "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
224
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
225
+ "model.layers.22.conv.conv.weight": "model.safetensors",
226
+ "model.layers.22.conv.in_proj.scales": "model.safetensors",
227
+ "model.layers.22.conv.in_proj.weight": "model.safetensors",
228
+ "model.layers.22.conv.out_proj.scales": "model.safetensors",
229
+ "model.layers.22.conv.out_proj.weight": "model.safetensors",
230
+ "model.layers.22.feed_forward.w1.scales": "model.safetensors",
231
+ "model.layers.22.feed_forward.w1.weight": "model.safetensors",
232
+ "model.layers.22.feed_forward.w2.scales": "model.safetensors",
233
+ "model.layers.22.feed_forward.w2.weight": "model.safetensors",
234
+ "model.layers.22.feed_forward.w3.scales": "model.safetensors",
235
+ "model.layers.22.feed_forward.w3.weight": "model.safetensors",
236
+ "model.layers.22.ffn_norm.weight": "model.safetensors",
237
+ "model.layers.22.operator_norm.weight": "model.safetensors",
238
+ "model.layers.23.conv.conv.weight": "model.safetensors",
239
+ "model.layers.23.conv.in_proj.scales": "model.safetensors",
240
+ "model.layers.23.conv.in_proj.weight": "model.safetensors",
241
+ "model.layers.23.conv.out_proj.scales": "model.safetensors",
242
+ "model.layers.23.conv.out_proj.weight": "model.safetensors",
243
+ "model.layers.23.feed_forward.w1.scales": "model.safetensors",
244
+ "model.layers.23.feed_forward.w1.weight": "model.safetensors",
245
+ "model.layers.23.feed_forward.w2.scales": "model.safetensors",
246
+ "model.layers.23.feed_forward.w2.weight": "model.safetensors",
247
+ "model.layers.23.feed_forward.w3.scales": "model.safetensors",
248
+ "model.layers.23.feed_forward.w3.weight": "model.safetensors",
249
+ "model.layers.23.ffn_norm.weight": "model.safetensors",
250
+ "model.layers.23.operator_norm.weight": "model.safetensors",
251
+ "model.layers.24.feed_forward.w1.scales": "model.safetensors",
252
+ "model.layers.24.feed_forward.w1.weight": "model.safetensors",
253
+ "model.layers.24.feed_forward.w2.scales": "model.safetensors",
254
+ "model.layers.24.feed_forward.w2.weight": "model.safetensors",
255
+ "model.layers.24.feed_forward.w3.scales": "model.safetensors",
256
+ "model.layers.24.feed_forward.w3.weight": "model.safetensors",
257
+ "model.layers.24.ffn_norm.weight": "model.safetensors",
258
+ "model.layers.24.operator_norm.weight": "model.safetensors",
259
+ "model.layers.24.self_attn.k_layernorm.weight": "model.safetensors",
260
+ "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
261
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
262
+ "model.layers.24.self_attn.out_proj.scales": "model.safetensors",
263
+ "model.layers.24.self_attn.out_proj.weight": "model.safetensors",
264
+ "model.layers.24.self_attn.q_layernorm.weight": "model.safetensors",
265
+ "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
266
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
267
+ "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
268
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
269
+ "model.layers.25.conv.conv.weight": "model.safetensors",
270
+ "model.layers.25.conv.in_proj.scales": "model.safetensors",
271
+ "model.layers.25.conv.in_proj.weight": "model.safetensors",
272
+ "model.layers.25.conv.out_proj.scales": "model.safetensors",
273
+ "model.layers.25.conv.out_proj.weight": "model.safetensors",
274
+ "model.layers.25.feed_forward.w1.scales": "model.safetensors",
275
+ "model.layers.25.feed_forward.w1.weight": "model.safetensors",
276
+ "model.layers.25.feed_forward.w2.scales": "model.safetensors",
277
+ "model.layers.25.feed_forward.w2.weight": "model.safetensors",
278
+ "model.layers.25.feed_forward.w3.scales": "model.safetensors",
279
+ "model.layers.25.feed_forward.w3.weight": "model.safetensors",
280
+ "model.layers.25.ffn_norm.weight": "model.safetensors",
281
+ "model.layers.25.operator_norm.weight": "model.safetensors",
282
+ "model.layers.26.conv.conv.weight": "model.safetensors",
283
+ "model.layers.26.conv.in_proj.scales": "model.safetensors",
284
+ "model.layers.26.conv.in_proj.weight": "model.safetensors",
285
+ "model.layers.26.conv.out_proj.scales": "model.safetensors",
286
+ "model.layers.26.conv.out_proj.weight": "model.safetensors",
287
+ "model.layers.26.feed_forward.w1.scales": "model.safetensors",
288
+ "model.layers.26.feed_forward.w1.weight": "model.safetensors",
289
+ "model.layers.26.feed_forward.w2.scales": "model.safetensors",
290
+ "model.layers.26.feed_forward.w2.weight": "model.safetensors",
291
+ "model.layers.26.feed_forward.w3.scales": "model.safetensors",
292
+ "model.layers.26.feed_forward.w3.weight": "model.safetensors",
293
+ "model.layers.26.ffn_norm.weight": "model.safetensors",
294
+ "model.layers.26.operator_norm.weight": "model.safetensors",
295
+ "model.layers.27.feed_forward.w1.scales": "model.safetensors",
296
+ "model.layers.27.feed_forward.w1.weight": "model.safetensors",
297
+ "model.layers.27.feed_forward.w2.scales": "model.safetensors",
298
+ "model.layers.27.feed_forward.w2.weight": "model.safetensors",
299
+ "model.layers.27.feed_forward.w3.scales": "model.safetensors",
300
+ "model.layers.27.feed_forward.w3.weight": "model.safetensors",
301
+ "model.layers.27.ffn_norm.weight": "model.safetensors",
302
+ "model.layers.27.operator_norm.weight": "model.safetensors",
303
+ "model.layers.27.self_attn.k_layernorm.weight": "model.safetensors",
304
+ "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
305
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
306
+ "model.layers.27.self_attn.out_proj.scales": "model.safetensors",
307
+ "model.layers.27.self_attn.out_proj.weight": "model.safetensors",
308
+ "model.layers.27.self_attn.q_layernorm.weight": "model.safetensors",
309
+ "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
310
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
311
+ "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
312
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
313
+ "model.layers.28.conv.conv.weight": "model.safetensors",
314
+ "model.layers.28.conv.in_proj.scales": "model.safetensors",
315
+ "model.layers.28.conv.in_proj.weight": "model.safetensors",
316
+ "model.layers.28.conv.out_proj.scales": "model.safetensors",
317
+ "model.layers.28.conv.out_proj.weight": "model.safetensors",
318
+ "model.layers.28.feed_forward.w1.scales": "model.safetensors",
319
+ "model.layers.28.feed_forward.w1.weight": "model.safetensors",
320
+ "model.layers.28.feed_forward.w2.scales": "model.safetensors",
321
+ "model.layers.28.feed_forward.w2.weight": "model.safetensors",
322
+ "model.layers.28.feed_forward.w3.scales": "model.safetensors",
323
+ "model.layers.28.feed_forward.w3.weight": "model.safetensors",
324
+ "model.layers.28.ffn_norm.weight": "model.safetensors",
325
+ "model.layers.28.operator_norm.weight": "model.safetensors",
326
+ "model.layers.29.conv.conv.weight": "model.safetensors",
327
+ "model.layers.29.conv.in_proj.scales": "model.safetensors",
328
+ "model.layers.29.conv.in_proj.weight": "model.safetensors",
329
+ "model.layers.29.conv.out_proj.scales": "model.safetensors",
330
+ "model.layers.29.conv.out_proj.weight": "model.safetensors",
331
+ "model.layers.29.feed_forward.w1.scales": "model.safetensors",
332
+ "model.layers.29.feed_forward.w1.weight": "model.safetensors",
333
+ "model.layers.29.feed_forward.w2.scales": "model.safetensors",
334
+ "model.layers.29.feed_forward.w2.weight": "model.safetensors",
335
+ "model.layers.29.feed_forward.w3.scales": "model.safetensors",
336
+ "model.layers.29.feed_forward.w3.weight": "model.safetensors",
337
+ "model.layers.29.ffn_norm.weight": "model.safetensors",
338
+ "model.layers.29.operator_norm.weight": "model.safetensors",
339
+ "model.layers.3.conv.conv.weight": "model.safetensors",
340
+ "model.layers.3.conv.in_proj.scales": "model.safetensors",
341
+ "model.layers.3.conv.in_proj.weight": "model.safetensors",
342
+ "model.layers.3.conv.out_proj.scales": "model.safetensors",
343
+ "model.layers.3.conv.out_proj.weight": "model.safetensors",
344
+ "model.layers.3.feed_forward.w1.scales": "model.safetensors",
345
+ "model.layers.3.feed_forward.w1.weight": "model.safetensors",
346
+ "model.layers.3.feed_forward.w2.scales": "model.safetensors",
347
+ "model.layers.3.feed_forward.w2.weight": "model.safetensors",
348
+ "model.layers.3.feed_forward.w3.scales": "model.safetensors",
349
+ "model.layers.3.feed_forward.w3.weight": "model.safetensors",
350
+ "model.layers.3.ffn_norm.weight": "model.safetensors",
351
+ "model.layers.3.operator_norm.weight": "model.safetensors",
352
+ "model.layers.4.conv.conv.weight": "model.safetensors",
353
+ "model.layers.4.conv.in_proj.scales": "model.safetensors",
354
+ "model.layers.4.conv.in_proj.weight": "model.safetensors",
355
+ "model.layers.4.conv.out_proj.scales": "model.safetensors",
356
+ "model.layers.4.conv.out_proj.weight": "model.safetensors",
357
+ "model.layers.4.feed_forward.w1.scales": "model.safetensors",
358
+ "model.layers.4.feed_forward.w1.weight": "model.safetensors",
359
+ "model.layers.4.feed_forward.w2.scales": "model.safetensors",
360
+ "model.layers.4.feed_forward.w2.weight": "model.safetensors",
361
+ "model.layers.4.feed_forward.w3.scales": "model.safetensors",
362
+ "model.layers.4.feed_forward.w3.weight": "model.safetensors",
363
+ "model.layers.4.ffn_norm.weight": "model.safetensors",
364
+ "model.layers.4.operator_norm.weight": "model.safetensors",
365
+ "model.layers.5.feed_forward.w1.scales": "model.safetensors",
366
+ "model.layers.5.feed_forward.w1.weight": "model.safetensors",
367
+ "model.layers.5.feed_forward.w2.scales": "model.safetensors",
368
+ "model.layers.5.feed_forward.w2.weight": "model.safetensors",
369
+ "model.layers.5.feed_forward.w3.scales": "model.safetensors",
370
+ "model.layers.5.feed_forward.w3.weight": "model.safetensors",
371
+ "model.layers.5.ffn_norm.weight": "model.safetensors",
372
+ "model.layers.5.operator_norm.weight": "model.safetensors",
373
+ "model.layers.5.self_attn.k_layernorm.weight": "model.safetensors",
374
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
375
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
376
+ "model.layers.5.self_attn.out_proj.scales": "model.safetensors",
377
+ "model.layers.5.self_attn.out_proj.weight": "model.safetensors",
378
+ "model.layers.5.self_attn.q_layernorm.weight": "model.safetensors",
379
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
380
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
381
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
382
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
383
+ "model.layers.6.conv.conv.weight": "model.safetensors",
384
+ "model.layers.6.conv.in_proj.scales": "model.safetensors",
385
+ "model.layers.6.conv.in_proj.weight": "model.safetensors",
386
+ "model.layers.6.conv.out_proj.scales": "model.safetensors",
387
+ "model.layers.6.conv.out_proj.weight": "model.safetensors",
388
+ "model.layers.6.feed_forward.w1.scales": "model.safetensors",
389
+ "model.layers.6.feed_forward.w1.weight": "model.safetensors",
390
+ "model.layers.6.feed_forward.w2.scales": "model.safetensors",
391
+ "model.layers.6.feed_forward.w2.weight": "model.safetensors",
392
+ "model.layers.6.feed_forward.w3.scales": "model.safetensors",
393
+ "model.layers.6.feed_forward.w3.weight": "model.safetensors",
394
+ "model.layers.6.ffn_norm.weight": "model.safetensors",
395
+ "model.layers.6.operator_norm.weight": "model.safetensors",
396
+ "model.layers.7.conv.conv.weight": "model.safetensors",
397
+ "model.layers.7.conv.in_proj.scales": "model.safetensors",
398
+ "model.layers.7.conv.in_proj.weight": "model.safetensors",
399
+ "model.layers.7.conv.out_proj.scales": "model.safetensors",
400
+ "model.layers.7.conv.out_proj.weight": "model.safetensors",
401
+ "model.layers.7.feed_forward.w1.scales": "model.safetensors",
402
+ "model.layers.7.feed_forward.w1.weight": "model.safetensors",
403
+ "model.layers.7.feed_forward.w2.scales": "model.safetensors",
404
+ "model.layers.7.feed_forward.w2.weight": "model.safetensors",
405
+ "model.layers.7.feed_forward.w3.scales": "model.safetensors",
406
+ "model.layers.7.feed_forward.w3.weight": "model.safetensors",
407
+ "model.layers.7.ffn_norm.weight": "model.safetensors",
408
+ "model.layers.7.operator_norm.weight": "model.safetensors",
409
+ "model.layers.8.conv.conv.weight": "model.safetensors",
410
+ "model.layers.8.conv.in_proj.scales": "model.safetensors",
411
+ "model.layers.8.conv.in_proj.weight": "model.safetensors",
412
+ "model.layers.8.conv.out_proj.scales": "model.safetensors",
413
+ "model.layers.8.conv.out_proj.weight": "model.safetensors",
414
+ "model.layers.8.feed_forward.w1.scales": "model.safetensors",
415
+ "model.layers.8.feed_forward.w1.weight": "model.safetensors",
416
+ "model.layers.8.feed_forward.w2.scales": "model.safetensors",
417
+ "model.layers.8.feed_forward.w2.weight": "model.safetensors",
418
+ "model.layers.8.feed_forward.w3.scales": "model.safetensors",
419
+ "model.layers.8.feed_forward.w3.weight": "model.safetensors",
420
+ "model.layers.8.ffn_norm.weight": "model.safetensors",
421
+ "model.layers.8.operator_norm.weight": "model.safetensors",
422
+ "model.layers.9.feed_forward.w1.scales": "model.safetensors",
423
+ "model.layers.9.feed_forward.w1.weight": "model.safetensors",
424
+ "model.layers.9.feed_forward.w2.scales": "model.safetensors",
425
+ "model.layers.9.feed_forward.w2.weight": "model.safetensors",
426
+ "model.layers.9.feed_forward.w3.scales": "model.safetensors",
427
+ "model.layers.9.feed_forward.w3.weight": "model.safetensors",
428
+ "model.layers.9.ffn_norm.weight": "model.safetensors",
429
+ "model.layers.9.operator_norm.weight": "model.safetensors",
430
+ "model.layers.9.self_attn.k_layernorm.weight": "model.safetensors",
431
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
432
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
433
+ "model.layers.9.self_attn.out_proj.scales": "model.safetensors",
434
+ "model.layers.9.self_attn.out_proj.weight": "model.safetensors",
435
+ "model.layers.9.self_attn.q_layernorm.weight": "model.safetensors",
436
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
438
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors"
440
+ }
441
+ }
mxfp4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
3
+ size 17905598
mxfp4/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": true,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000000000019884624838656,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "TokenizersBackend",
12
+ "use_default_system_prompt": false
13
+ }
mxfp8/chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
3
+
4
+ {%- macro format_arg_value(arg_value) -%}
5
+ {%- if arg_value is string -%}
6
+ {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
7
+ {%- elif arg_value is mapping or arg_value is iterable -%}
8
+ {{- arg_value | tojson -}}
9
+ {%- else -%}
10
+ {{- arg_value | string -}}
11
+ {%- endif -%}
12
+ {%- endmacro -%}
13
+
14
+ {%- macro parse_content(content) -%}
15
+ {%- if content is string -%}
16
+ {{- content -}}
17
+ {%- elif content is mapping -%}
18
+ {{- content | tojson -}}
19
+ {%- elif content is iterable -%}
20
+ {%- set _ns = namespace(result="") -%}
21
+ {%- for item in content -%}
22
+ {%- if item is string -%}
23
+ {%- set _ns.result = _ns.result + item -%}
24
+ {%- elif item is mapping and item.get("type") == "image" -%}
25
+ {%- set _ns.result = _ns.result + "<image>" -%}
26
+ {%- elif item is mapping and item.get("type") == "text" -%}
27
+ {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
28
+ {%- else -%}
29
+ {%- set _ns.result = _ns.result + (item | tojson) -%}
30
+ {%- endif -%}
31
+ {%- endfor -%}
32
+ {{- _ns.result -}}
33
+ {%- endif -%}
34
+ {%- endmacro -%}
35
+
36
+ {%- macro render_tool_calls(tool_calls) -%}
37
+ {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
38
+ {%- for tool_call in tool_calls -%}
39
+ {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
40
+ {%- set func_name = func["name"] -%}
41
+ {%- set func_args = func.get("arguments") -%}
42
+ {%- set args_ns = namespace(arg_strings=[]) -%}
43
+ {%- if func_args is mapping -%}
44
+ {%- for arg_name, arg_value in func_args.items() -%}
45
+ {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
46
+ {%- endfor -%}
47
+ {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
48
+ {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
49
+ {%- endif -%}
50
+ {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
51
+ {%- endfor -%}
52
+ {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
53
+ {%- endmacro -%}
54
+
55
+ {%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
56
+ {%- if messages and messages[0]["role"] == "system" -%}
57
+ {%- if messages[0].get("content") -%}
58
+ {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
59
+ {%- endif -%}
60
+ {%- set messages = messages[1:] -%}
61
+ {%- endif -%}
62
+ {%- if tools -%}
63
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
64
+ {%- for tool in tools -%}
65
+ {%- if tool is not string -%}
66
+ {%- set tool = tool | tojson -%}
67
+ {%- endif -%}
68
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
69
+ {%- if not loop.last -%}
70
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
71
+ {%- endif -%}
72
+ {%- endfor -%}
73
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
74
+ {%- endif -%}
75
+ {%- if ns.system_prompt -%}
76
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
77
+ {%- endif -%}
78
+ {%- for message in messages -%}
79
+ {%- if message["role"] == "user" -%}
80
+ {%- set ns.last_user_index = loop.index0 -%}
81
+ {%- endif -%}
82
+ {%- endfor -%}
83
+ {%- for message in messages -%}
84
+ {{- "<|im_start|>" + message.role + "\n" -}}
85
+ {%- if message.role == "assistant" -%}
86
+ {%- generation -%}
87
+ {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
88
+ {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
89
+ {%- set thinking = thinking if thinking is string else "" -%}
90
+ {%- if thinking and keep_thinking -%}
91
+ {{- "<think>" + thinking + "</think>" -}}
92
+ {%- endif -%}
93
+ {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
94
+ {%- set _has_cfm = false -%}
95
+ {%- set content = "" -%}
96
+ {%- if message.get("content") -%}
97
+ {%- set content = parse_content(message.content) -%}
98
+ {%- endif -%}
99
+ {%- if not keep_thinking and "</think>" in content -%}
100
+ {%- set content = content.split("</think>")[-1] | trim -%}
101
+ {%- endif -%}
102
+ {%- if content.endswith(_cfm_tag) -%}
103
+ {%- set _has_cfm = true -%}
104
+ {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
105
+ {%- set content = content[:_trunc_len] -%}
106
+ {%- endif -%}
107
+ {{- content -}}
108
+ {%- if message.tool_calls -%}
109
+ {{- render_tool_calls(message.tool_calls) -}}
110
+ {%- endif -%}
111
+ {%- if _has_cfm -%}
112
+ {{- _cfm_tag -}}
113
+ {%- endif -%}
114
+ {{- "<|im_end|>\n" -}}
115
+ {%- endgeneration -%}
116
+ {%- else %}
117
+ {%- if message.get("content") -%}
118
+ {{- parse_content(message["content"]) -}}
119
+ {%- endif -%}
120
+ {{- "<|im_end|>\n" -}}
121
+ {%- endif %}
122
+ {%- endfor -%}
123
+ {%- if add_generation_prompt -%}
124
+ {{- "<|im_start|>assistant\n<think>" -}}
125
+ {%- endif -%}
mxfp8/config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": false,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 10752,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 124894,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": [
22
+ 124900
23
+ ],
24
+ "hidden_size": 2048,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 10752,
27
+ "layer_types": [
28
+ "conv",
29
+ "conv",
30
+ "full_attention",
31
+ "conv",
32
+ "conv",
33
+ "full_attention",
34
+ "conv",
35
+ "conv",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "conv",
40
+ "conv",
41
+ "full_attention",
42
+ "conv",
43
+ "conv",
44
+ "conv",
45
+ "full_attention",
46
+ "conv",
47
+ "conv",
48
+ "conv",
49
+ "full_attention",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv",
54
+ "conv",
55
+ "full_attention",
56
+ "conv",
57
+ "conv"
58
+ ],
59
+ "max_position_embeddings": 128000,
60
+ "model_type": "lfm2",
61
+ "norm_eps": 1e-05,
62
+ "num_attention_heads": 32,
63
+ "num_heads": 32,
64
+ "num_hidden_layers": 30,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 124893,
67
+ "quantization": {
68
+ "group_size": 32,
69
+ "bits": 8,
70
+ "mode": "mxfp8"
71
+ },
72
+ "quantization_config": {
73
+ "group_size": 32,
74
+ "bits": 8,
75
+ "mode": "mxfp8"
76
+ },
77
+ "rope_parameters": {
78
+ "rope_theta": 10000000.0,
79
+ "rope_type": "default"
80
+ },
81
+ "rope_theta": 10000000.0,
82
+ "tie_word_embeddings": true,
83
+ "transformers_version": "5.2.0",
84
+ "use_cache": true,
85
+ "use_pos_enc": true,
86
+ "vocab_size": 128000
87
+ }
mxfp8/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 124894,
4
+ "eos_token_id": [
5
+ 124900
6
+ ],
7
+ "output_attentions": false,
8
+ "output_hidden_states": false,
9
+ "pad_token_id": 124893,
10
+ "temperature": 0.2,
11
+ "top_k": 80,
12
+ "repetition_penalty": 1.05,
13
+ "transformers_version": "5.2.0",
14
+ "use_cache": true
15
+ }
mxfp8/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66100ccb661c1f3c150e652a7d4c65162cbe1669fd9d37bf0dfbb52c678f0efe
3
+ size 2781787434