Instructions to use llm-jp/llm-jp-3-8x1.8b-instruct2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llm-jp/llm-jp-3-8x1.8b-instruct2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="llm-jp/llm-jp-3-8x1.8b-instruct2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("llm-jp/llm-jp-3-8x1.8b-instruct2")
model = AutoModelForCausalLM.from_pretrained("llm-jp/llm-jp-3-8x1.8b-instruct2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use llm-jp/llm-jp-3-8x1.8b-instruct2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llm-jp/llm-jp-3-8x1.8b-instruct2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-jp/llm-jp-3-8x1.8b-instruct2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llm-jp/llm-jp-3-8x1.8b-instruct2

SGLang

How to use llm-jp/llm-jp-3-8x1.8b-instruct2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "llm-jp/llm-jp-3-8x1.8b-instruct2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-jp/llm-jp-3-8x1.8b-instruct2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "llm-jp/llm-jp-3-8x1.8b-instruct2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "llm-jp/llm-jp-3-8x1.8b-instruct2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llm-jp/llm-jp-3-8x1.8b-instruct2 with Docker Model Runner:
```
docker model run hf.co/llm-jp/llm-jp-3-8x1.8b-instruct2
```

Taka008 commited on Apr 1, 2025

Commit

e2eca1b

2 Parent(s): 2216185 c72db53

merge bf16

Browse files

Files changed (10) hide show

config.json +1 -1
model-00001-of-00008.safetensors → model-00001-of-00004.safetensors +2 -2
model-00002-of-00008.safetensors → model-00002-of-00004.safetensors +2 -2
model-00003-of-00008.safetensors → model-00003-of-00004.safetensors +2 -2
model-00004-of-00008.safetensors → model-00004-of-00004.safetensors +2 -2
model-00005-of-00008.safetensors +0 -3
model-00006-of-00008.safetensors +0 -3
model-00007-of-00008.safetensors +0 -3
model-00008-of-00008.safetensors +0 -3
model.safetensors.index.json +0 -0

@@ -27,7 +27,7 @@
   "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 99584

   "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 99584

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4726150c846e85a998d0a971e2ee895c8d1ad100097c6bd4108b8254a9829fe
-size 4951616224

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16e996e7dd279b768c00bda87f87181863af575293028fcd76fbe6f0dd5dc114
-size 4966397176

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e099aeb88c6ea29c34bcb3fbe523cffb2c1f33ce375923673a5cab98577e9b
-size 4957925968

 version https://git-lfs.github.com/spec/v1
+oid sha256:8276058eddf5d0546b6222d8961042ee59c73a5124c70fed5899b5b38182a45e
+size 4988379392

 version https://git-lfs.github.com/spec/v1
+oid sha256:c9f72ff0b40dedfa3f2a46fbc2c26426e510c88bb0e4f82591d54421334a745a
+size 4987299352

 version https://git-lfs.github.com/spec/v1
+oid sha256:b304793c4ce0026624adf204b504d1a4271fde46ea6f9099083d39b50386181e
+size 4991535416

 version https://git-lfs.github.com/spec/v1
+oid sha256:017c7a8406758569399e031d21aa0cf66062307896f23914e18cf7f8c330ffc7
+size 3566400304

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bf0046e1ff49331621ff887efd3567c2361ae5234cc1bb26591190cd4506c4b6
-size 4966397280