Instructions to use p1atdev/llm-jp-3-3.7b-instruct2-R27 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use p1atdev/llm-jp-3-3.7b-instruct2-R27 with Transformers:

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

pipe = pipeline("text-generation", model="p1atdev/llm-jp-3-3.7b-instruct2-R27")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("p1atdev/llm-jp-3-3.7b-instruct2-R27")
model = AutoModelForCausalLM.from_pretrained("p1atdev/llm-jp-3-3.7b-instruct2-R27")
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

vLLM

How to use p1atdev/llm-jp-3-3.7b-instruct2-R27 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "p1atdev/llm-jp-3-3.7b-instruct2-R27"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "p1atdev/llm-jp-3-3.7b-instruct2-R27",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/p1atdev/llm-jp-3-3.7b-instruct2-R27

SGLang

How to use p1atdev/llm-jp-3-3.7b-instruct2-R27 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 "p1atdev/llm-jp-3-3.7b-instruct2-R27" \
    --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": "p1atdev/llm-jp-3-3.7b-instruct2-R27",
		"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 "p1atdev/llm-jp-3-3.7b-instruct2-R27" \
        --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": "p1atdev/llm-jp-3-3.7b-instruct2-R27",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use p1atdev/llm-jp-3-3.7b-instruct2-R27 with Docker Model Runner:
```
docker model run hf.co/p1atdev/llm-jp-3-3.7b-instruct2-R27
```

p1atdev commited on Feb 14, 2025

Commit

add8e2a

1 Parent(s): b9d9415

Training in progress, step 1980

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -68,7 +68,7 @@
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}\n\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n        {{- '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}\n    {%- elif message['role'] == 'user' %}\n        {{- '\n\n### 指示:\n' + message['content'] }}\n        {%- if additional_instruction is defined and additional_instruction != '' %}\n            {{- '\n\n' + additional_instruction }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '\n\n### 応答:\n' + message['content'] + eos_token }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- '\n\n### 応答:\n' }}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "cls_token": "<CLS|LLM-jp>",
   "eod_token": "</s>",

     }
   },
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}\n\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n        {{- '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}\n    {%- elif message['role'] == 'user' %}\n        {{- '\n\n### 指示:\n' + message['content'] }}\n        {%- if additional_instruction is not none and additional_instruction != '' %}\n            {{- '\n\n' + additional_instruction }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- '\n\n### 応答:\n' + message['content'] + eos_token }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- '\n\n### 応答:\n' }}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "cls_token": "<CLS|LLM-jp>",
   "eod_token": "</s>",