Instructions to use llm-jp/llm-jp-3-172b-instruct3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llm-jp/llm-jp-3-172b-instruct3 with Transformers:

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

pipe = pipeline("text-generation", model="llm-jp/llm-jp-3-172b-instruct3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("llm-jp/llm-jp-3-172b-instruct3")
model = AutoModelForMultimodalLM.from_pretrained("llm-jp/llm-jp-3-172b-instruct3")
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-3-172b-instruct3 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-3-172b-instruct3"
# 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-3-172b-instruct3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llm-jp/llm-jp-3-172b-instruct3

SGLang

How to use llm-jp/llm-jp-3-172b-instruct3 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-3-172b-instruct3" \
    --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-3-172b-instruct3",
		"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-3-172b-instruct3" \
        --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-3-172b-instruct3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use llm-jp/llm-jp-3-172b-instruct3 with Docker Model Runner:
```
docker model run hf.co/llm-jp/llm-jp-3-172b-instruct3
```

hkiyomaru commited on Jan 20, 2025

Commit

33b7c54

1 Parent(s): 44cd626

update LICENSE

Browse files

Files changed (1) hide show

LICENSE +2 -2

LICENSE CHANGED Viewed

@@ -6,7 +6,7 @@ This llm-jp-3-172b-instruct 3 License Agreement sets forth the terms and conditi
 Article 1 Definitions
 (1) "Agreement" means the llm-jp-3-172b-instruct3 License Agreement.
-(2) "ROIS" means the Research Organization of Information and Systems, Inter- University Research Institute Corporation and "NII" means the National Institute of Informatics.
 (3) "Model" means the learned parameters named "llm-jp-3-172b-instruct3.”
 (4) "User" means any individual or legal entity that uses the Model.
 (5) "License" means permission by ROIS for the User to use the Model in accordance with the terms and conditions of this Agreement.
@@ -32,7 +32,7 @@ With respect to the use of the Model and Output, the User shall not engage in an
 (4) Any act that causes, or may cause, economic damage to ROIS, NII, or any third party;
 (5) Making threatening, racially discriminatory, or defamatory statements;
 (6) Stalking, harassing, or trolling other Users, or use to expose personal information;
-(7) Use in the development, etc. of computer viruses, malicious software or harmful programs;
 (8) Use in communication, conduct, or expression that may incite or encourage harmful behavior such as suicide, self-harm, violence, or drug use;
 (9) Use to generate or convey false information;
 (10) Involvement in, or implying involvement in, criminal activities or acts related to criminal activities, or aiding and abetting such activities;

 Article 1 Definitions
 (1) "Agreement" means the llm-jp-3-172b-instruct3 License Agreement.
+(2) "ROIS" means the Research Organization of Information and Systems, Inter-University Research Institute Corporation and "NII" means the National Institute of Informatics.
 (3) "Model" means the learned parameters named "llm-jp-3-172b-instruct3.”
 (4) "User" means any individual or legal entity that uses the Model.
 (5) "License" means permission by ROIS for the User to use the Model in accordance with the terms and conditions of this Agreement.
 (4) Any act that causes, or may cause, economic damage to ROIS, NII, or any third party;
 (5) Making threatening, racially discriminatory, or defamatory statements;
 (6) Stalking, harassing, or trolling other Users, or use to expose personal information;
+(7) Use in the development, etc. of computer viruses, malicious software, or harmful programs;
 (8) Use in communication, conduct, or expression that may incite or encourage harmful behavior such as suicide, self-harm, violence, or drug use;
 (9) Use to generate or convey false information;
 (10) Involvement in, or implying involvement in, criminal activities or acts related to criminal activities, or aiding and abetting such activities;