Instructions to use OpenRLHF/Llama-3-8b-sft-mixture with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenRLHF/Llama-3-8b-sft-mixture with Transformers:

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

pipe = pipeline("text-generation", model="OpenRLHF/Llama-3-8b-sft-mixture")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenRLHF/Llama-3-8b-sft-mixture")
model = AutoModelForCausalLM.from_pretrained("OpenRLHF/Llama-3-8b-sft-mixture")
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 OpenRLHF/Llama-3-8b-sft-mixture with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenRLHF/Llama-3-8b-sft-mixture"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenRLHF/Llama-3-8b-sft-mixture",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenRLHF/Llama-3-8b-sft-mixture

SGLang

How to use OpenRLHF/Llama-3-8b-sft-mixture 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 "OpenRLHF/Llama-3-8b-sft-mixture" \
    --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": "OpenRLHF/Llama-3-8b-sft-mixture",
		"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 "OpenRLHF/Llama-3-8b-sft-mixture" \
        --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": "OpenRLHF/Llama-3-8b-sft-mixture",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenRLHF/Llama-3-8b-sft-mixture with Docker Model Runner:
```
docker model run hf.co/OpenRLHF/Llama-3-8b-sft-mixture
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT

We fixed the generation_config.json.

This is the SFT checkpoint used for the project Online-RLHF. Also, check the technical report here.

The model is trained from 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.

The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract.

Downloads last month: 4,536

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for OpenRLHF/Llama-3-8b-sft-mixture

Finetunes

11 models

Quantizations

2 models

Spaces using OpenRLHF/Llama-3-8b-sft-mixture 9

Paper for OpenRLHF/Llama-3-8b-sft-mixture

RLHF Workflow: From Reward Modeling to Online RLHF

Paper • 2405.07863 • Published May 13, 2024 • 71