Instructions to use RLHFlow/Llama3.1-8B-ORM-Mistral-Data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RLHFlow/Llama3.1-8B-ORM-Mistral-Data with Transformers:

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

pipe = pipeline("text-generation", model="RLHFlow/Llama3.1-8B-ORM-Mistral-Data")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RLHFlow/Llama3.1-8B-ORM-Mistral-Data")
model = AutoModelForCausalLM.from_pretrained("RLHFlow/Llama3.1-8B-ORM-Mistral-Data")
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/Llama3.1-8B-ORM-Mistral-Data with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RLHFlow/Llama3.1-8B-ORM-Mistral-Data"
# 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/Llama3.1-8B-ORM-Mistral-Data",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RLHFlow/Llama3.1-8B-ORM-Mistral-Data

SGLang

How to use RLHFlow/Llama3.1-8B-ORM-Mistral-Data 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/Llama3.1-8B-ORM-Mistral-Data" \
    --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/Llama3.1-8B-ORM-Mistral-Data",
		"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/Llama3.1-8B-ORM-Mistral-Data" \
        --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/Llama3.1-8B-ORM-Mistral-Data",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RLHFlow/Llama3.1-8B-ORM-Mistral-Data with Docker Model Runner:
```
docker model run hf.co/RLHFlow/Llama3.1-8B-ORM-Mistral-Data
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a outcome-supervised reward (ORM) trained on Mistral-generated data from the project RLHFlow/RLHF-Reward-Modeling

The model is trained from meta-llama/Llama-3.1-8B-Instruct on RLHFlow/Mistral-ORM-Data for 1 epochs. We use a global batch size of 32 and a learning rate of 2e-6, where we pack the samples and split them into chunks of 8192 token. See more training details at https://github.com/RLHFlow/Online-RLHF/blob/main/math/llama-3.1-prm.yaml .

BoN evaluation result for Mistral generator:

Model	Method	GSM8K	MATH
Mistral-7B	Pass@1	77.9	28.4
Mistral-7B	Majority Voting@1024	84.2	36.8
Mistral-7B	Mistral-ORM@1024	90.1	43.6
Mistral-7B	Mistral-PRM@1024	92.4	46.3

Scaling the inference sampling to N=1024 for Deepseek generator:

Model	Method	GSM8K	MATH
Deepseek-7B	Pass@1	83.9	38.4
Deepseek-7B	Majority Voting@1024	89.7	57.4
Deepseek-7B	Deepseek-ORM@1024	93.4	52.4
Deepseek-7B	Deepseek-PRM@1024	93.0	58.1
Deepseek-7B	Mistral-ORM@1024 (OOD)	90.3	54.9
Deepseek-7B	Mistral-PRM@1024 (OOD)	91.9	56.9

Visualization

Usage

See https://github.com/RLHFlow/RLHF-Reward-Modeling/tree/main/math for detailed examples.

Citation

The automatic annotation was proposed in the Math-shepherd paper:

@inproceedings{wang2024math,
  title={Math-shepherd: Verify and reinforce llms step-by-step without human annotations},
  author={Wang, Peiyi and Li, Lei and Shao, Zhihong and Xu, Runxin and Dai, Damai and Li, Yifei and Chen, Deli and Wu, Yu and Sui, Zhifang},
  booktitle={Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages={9426--9439},
  year={2024}
}

If you find the training recipe useful, please consider cite it as follows.

@misc{xiong2024rlhflowmath,
      author={Wei Xiong and Hanning Zhang and Nan Jiang and Tong Zhang},
  title = {An Implementation of Generative PRM},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/RLHFlow/RLHF-Reward-Modeling}}
}

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for RLHFlow/Llama3.1-8B-ORM-Mistral-Data

Quantizations

1 model

Collection including RLHFlow/Llama3.1-8B-ORM-Mistral-Data

RLHFlow MATH Process Reward Model

Collection

This is a collection of datasets and models of process reward modeling. • 14 items • Updated Mar 2 • 11