Instructions to use RLHFlow/LLaMA3-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RLHFlow/LLaMA3-SFT with Transformers:

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

pipe = pipeline("text-generation", model="RLHFlow/LLaMA3-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RLHFlow/LLaMA3-SFT")
model = AutoModelForCausalLM.from_pretrained("RLHFlow/LLaMA3-SFT")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RLHFlow/LLaMA3-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RLHFlow/LLaMA3-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RLHFlow/LLaMA3-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RLHFlow/LLaMA3-SFT

SGLang

How to use RLHFlow/LLaMA3-SFT 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 "RLHFlow/LLaMA3-SFT" \
    --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": "RLHFlow/LLaMA3-SFT",
		"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 "RLHFlow/LLaMA3-SFT" \
        --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": "RLHFlow/LLaMA3-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RLHFlow/LLaMA3-SFT with Docker Model Runner:
```
docker model run hf.co/RLHFlow/LLaMA3-SFT
```

LLaMA3.1-SFT

by jackzhang - opened Sep 17, 2024

Discussion

jackzhang

Sep 17, 2024

Hello,

Thanks for open sourcing this SFT checkpoint, it has been extremely instrumental to my research! Since Llama3.1 has been released by Meta, I'm wondering if you plan to release a version of the SFT model based on Llama3.1 instead of Llama3?

Thanks!

weqweasdas

RLHFlow org Sep 17, 2024

sure. we have a gemma-2-2b model here sfairXC/gemma-sft-1ep

I will ask my collaborators to present llama 3.1 and gemma2-9b.

jackzhang

Sep 19, 2024

Thank you! I saw a model here: sfairXC/llama-3.1-sft-1ep

Is this model fine-tuned with the same data mixture and hyperparameters described in the RLHF Workflow paper?

weqweasdas

RLHFlow org Sep 19, 2024

Yes. You are correct.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment