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
```

weqweasdas commited on Nov 3, 2024

Commit

465c80f

verified ·

1 Parent(s): 0a31e34

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

	@@ -11,3 +11,27 @@ This is the SFT checkpoint used for the project [RLHFlow/Online-RLHF](https://gi
11
12	The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.
13

 The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.
+## Academic Benchmarks
+| **Model**                  | **Size** | **Method**      | **LC AlpacaEval** | **MT-Bench** | **GSM-8K** | **MMLU** | **HumanEval** | **TruthfulQA** | **ARC** | **MBPP** |
+|----------------------------|----------|-----------------|------------|------------|------------|----------|---------------|----------------|---------|----------|
+| LLaMA-3-8B-it              | 8B       | RS+DPO+PPO      |22.9|8.16| 79.6       | 66.0     | 61.6          | 43.9           | 59.5    | 61.1     |
+| Ours (SFT baseline)        | 8B       | SFT             |10.2|7.69| 74.2       | 64.7     | 65.2          | 53.4           | 61.4    | 62.3     |
+| Ours (Iterative RLHF)      | 8B       | Iterative DPO   |37.2|8.46| 80.7       | 65.3     | 64.6          | 60.4           | 64.3    | 60.8     |
+## Citation
+Please cite our techical report if you find our model is useful for your research or product.
+```
+@misc{dong2024rlhf,
+      title={RLHF Workflow: From Reward Modeling to Online RLHF},
+      author={Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang},
+      year={2024},
+      eprint={2405.07863},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```