Instructions to use chujiezheng/LLaMA3-iterative-DPO-final-ExPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chujiezheng/LLaMA3-iterative-DPO-final-ExPO with Transformers:

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

pipe = pipeline("text-generation", model="chujiezheng/LLaMA3-iterative-DPO-final-ExPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chujiezheng/LLaMA3-iterative-DPO-final-ExPO")
model = AutoModelForCausalLM.from_pretrained("chujiezheng/LLaMA3-iterative-DPO-final-ExPO")
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 chujiezheng/LLaMA3-iterative-DPO-final-ExPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/chujiezheng/LLaMA3-iterative-DPO-final-ExPO

SGLang

How to use chujiezheng/LLaMA3-iterative-DPO-final-ExPO 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 "chujiezheng/LLaMA3-iterative-DPO-final-ExPO" \
    --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": "chujiezheng/LLaMA3-iterative-DPO-final-ExPO",
		"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 "chujiezheng/LLaMA3-iterative-DPO-final-ExPO" \
        --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": "chujiezheng/LLaMA3-iterative-DPO-final-ExPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use chujiezheng/LLaMA3-iterative-DPO-final-ExPO with Docker Model Runner:
```
docker model run hf.co/chujiezheng/LLaMA3-iterative-DPO-final-ExPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LLaMA3-iterative-DPO-final-ExPO

The extrapolated (ExPO) model based on RLHFlow/LLaMA3-iterative-DPO-final and RLHFlow/LLaMA3-SFT, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper.

Specifically, we obtain this model by extrapolating (alpha = 0.3) from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference.

Evaluation Results

Evaluation results on the AlpacaEval 2.0 benchmark (you can find the evaluation outputs on the official GitHub repo):

	Win Rate (Ori)	LC Win Rate (Ori)	Win Rate (+ ExPO)	LC Win Rate (+ ExPO)
`HuggingFaceH4/zephyr-7b-alpha`	6.7%	10.0%	10.6%	13.6%
`HuggingFaceH4/zephyr-7b-beta`	10.2%	13.2%	11.1%	14.0%
`berkeley-nest/Starling-LM-7B-alpha`	15.0%	18.3%	18.2%	19.5%
`Nexusflow/Starling-LM-7B-beta`	26.6%	25.8%	29.6%	26.4%
`snorkelai/Snorkel-Mistral-PairRM`	24.7%	24.0%	28.8%	26.4%
`RLHFlow/LLaMA3-iterative-DPO-final`	29.2%	36.0%	32.7%	37.8%
`internlm/internlm2-chat-1.8b`	3.8%	4.0%	5.2%	4.3%
`internlm/internlm2-chat-7b`	20.5%	18.3%	28.1%	22.7%
`internlm/internlm2-chat-20b`	36.1%	24.9%	46.2%	27.2%
`allenai/tulu-2-dpo-7b`	8.5%	10.2%	11.5%	11.7%
`allenai/tulu-2-dpo-13b`	11.2%	15.5%	15.6%	17.6%
`allenai/tulu-2-dpo-70b`	15.4%	21.2%	23.0%	25.7%

Evaluation results on the MT-Bench benchmark (you can find the evaluation outputs on the official GitHub repo):

	Original	+ ExPO
`HuggingFaceH4/zephyr-7b-alpha`	6.85	6.87
`HuggingFaceH4/zephyr-7b-beta`	7.02	7.06
`berkeley-nest/Starling-LM-7B-alpha`	7.82	7.91
`Nexusflow/Starling-LM-7B-beta`	8.10	8.18
`snorkelai/Snorkel-Mistral-PairRM`	7.63	7.69
`RLHFlow/LLaMA3-iterative-DPO-final`	8.08	8.45
`internlm/internlm2-chat-1.8b`	5.17	5.26
`internlm/internlm2-chat-7b`	7.72	7.80
`internlm/internlm2-chat-20b`	8.13	8.26
`allenai/tulu-2-dpo-7b`	6.35	6.38
`allenai/tulu-2-dpo-13b`	7.00	7.26
`allenai/tulu-2-dpo-70b`	7.79	8.03