Upload skillrep-reranker-0.6b

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,144 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-Reranker-0.6B
+library_name: transformers
+pipeline_tag: text-ranking
+tags:
+  - reranker
+  - cross-encoder
+  - retrieval
+  - agent-skills
+  - skill-routing
+  - skillcorpus
+language:
+  - en
+---
+
+# skillrep-reranker-0.6b
+
+A cross-encoder for **agent-skill retrieval**: given a task description and a
+candidate skill document, judge whether the skill helps complete the task.
+Fine-tuned from
+[Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B).
+
+It reorders the candidates recalled by
+[skillrep-embedding-0.6b](https://huggingface.co/EverMind-AI/skillrep-embedding-0.6b).
+Scoring is one forward pass per (task, skill) pair, so run it on a shortlist,
+the encoder's top 10, not on the whole registry. Skill documents follow the
+schema of
+[skillcorpus-demo-1k](https://huggingface.co/datasets/EverMind-AI/skillcorpus-demo-1k).
+
+| Property | Value |
+|---|---|
+| Parameters | 596M |
+| Layers | 28 |
+| Precision | bfloat16 |
+| Output | `logit("yes") - logit("no")` at the final position |
+
+Requires `transformers>=4.56` (the `dtype=` argument was named `torch_dtype=`
+before that).
+
+## Usage
+
+The model answers a yes/no question, and the relevance score is the difference
+between the `yes` and `no` logits at the final position. `sigmoid` of this score
+is `P("yes")` and gives the same ordering.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL = "EverMind-AI/skillrep-reranker-0.6b"
+tok = AutoTokenizer.from_pretrained(MODEL, padding_side="left")
+model = AutoModelForCausalLM.from_pretrained(MODEL, dtype=torch.bfloat16).cuda().eval()
+
+PREFIX = ('<|im_start|>system\nJudge whether the Document meets the requirements '
+          'based on the Query and the Instruct provided. Note that the answer can '
+          'only be "yes" or "no".<|im_end|>\n<|im_start|>user\n')
+SUFFIX = '<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n'
+INSTRUCT = ("Given a coding task description, judge whether the skill document "
+            "is relevant and useful for completing the task")
+
+YES, NO = tok.convert_tokens_to_ids("yes"), tok.convert_tokens_to_ids("no")
+PRE = tok.encode(PREFIX, add_special_tokens=False)
+SUF = tok.encode(SUFFIX, add_special_tokens=False)
+
+
+def pair(task, skill):
+    doc = f"{skill['name']} | {skill['description'][:500]} | {skill['body'][:2000]}"
+    return f"<Instruct>: {INSTRUCT}\n\n<Query>: {task}\n\n<Document>: {doc}"
+
+
+def score(task, skills, max_length=4096):
+    """One score per skill; higher means more relevant."""
+    budget = max_length - len(PRE) - len(SUF)       # truncate the pair, never the template
+    ids = [PRE + tok.encode(pair(task, s), add_special_tokens=False,
+                            truncation=True, max_length=budget) + SUF for s in skills]
+    batch = tok.pad({"input_ids": ids}, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        logits = model(**batch).logits[:, -1, :]
+    return (logits[:, YES] - logits[:, NO]).float().tolist()
+
+
+task = "resolve conflicts after a git merge"
+skills = [
+    {"name": "resolve-conflicts", "description": "Resolve git merge conflicts.",
+     "body": "# Resolving merge conflicts\n1. Run `git status` to list conflicted files ..."},
+    {"name": "sourdough", "description": "Bake sourdough bread.",
+     "body": "# Sourdough\nMix flour, water and starter ..."},
+]
+print(score(task, skills))
+# -> [3.0, -4.06]
+```
+
+Exact scores shift in the last decimal with dtype and hardware; the ordering is
+what matters.
+
+Keep the `PREFIX` / `SUFFIX` template and the `<Instruct>` / `<Query>` /
+`<Document>` layout, with blank lines between the parts, exactly as above. The
+score is read off the final-position logits, so truncate the pair text, not the
+template.
+
+### Reranking a shortlist
+
+```python
+# candidates: the top 10 skills that skillrep-embedding-0.6b returns for `task`
+scores = score(task, candidates)
+reranked = [c for _, c in sorted(zip(scores, candidates), key=lambda x: -x[0])]
+```
+
+### Via the chat template
+
+`chat_template.jinja` reproduces the prompt string above, so the tokenizer can
+assemble it instead. It reads three roles: `system` carries the instruction
+(omit it to get the default shown above), `query` the task, and `document` the
+skill:
+
+```python
+prompt = tok.apply_chat_template([
+    {"role": "query",    "content": task},
+    {"role": "document", "content": "resolve-conflicts | Resolve git merge conflicts. | ..."},
+], tokenize=False)
+```
+
+### Input lengths
+
+| input | limit |
+|---|---|
+| task description | not cut by characters |
+| skill `description` | first 500 characters |
+| skill `body` | first 2,000 characters |
+| whole prompt | 4,096 tokens, cutting the pair text and keeping the template |
+
+## Intended use
+
+Second-stage reranking of the top 10 candidates that
+[skillrep-embedding-0.6b](https://huggingface.co/EverMind-AI/skillrep-embedding-0.6b)
+recalls for a task. Treat the output as a ranking signal rather than a
+calibrated probability: compare scores within one candidate list, not across
+different tasks.
+
+## License
+
+Apache-2.0, inherited from the base model. Skills keep their own upstream
+licenses.

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,17 @@
+{%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a coding task description, judge whether the skill document is relevant and useful for completing the task") -%}
+{%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%}
+{%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%}
+<|im_start|>system
+Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
+<|im_start|>user
+<Instruct>: {{ instruction }}
+
+<Query>: {{ query_text }}
+
+<Document>: {{ document_text }}<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669,
+  "rope_theta": 1000000
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8e5001e1fd29d4813613619ff94f8d67bca920f47ac1abd6a2407701c5443e
+size 1191588280

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a01676060aa035ffebeb8a78c23b1074c2ca1b57082f8839255317a4108309e
+size 11422749

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}