Instructions to use kaist-ai/mistral-orpo-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaist-ai/mistral-orpo-alpha with Transformers:

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

pipe = pipeline("text-generation", model="kaist-ai/mistral-orpo-alpha")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kaist-ai/mistral-orpo-alpha")
model = AutoModelForCausalLM.from_pretrained("kaist-ai/mistral-orpo-alpha")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kaist-ai/mistral-orpo-alpha with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaist-ai/mistral-orpo-alpha

SGLang

How to use kaist-ai/mistral-orpo-alpha 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 "kaist-ai/mistral-orpo-alpha" \
    --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": "kaist-ai/mistral-orpo-alpha",
		"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 "kaist-ai/mistral-orpo-alpha" \
        --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": "kaist-ai/mistral-orpo-alpha",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kaist-ai/mistral-orpo-alpha with Docker Model Runner:
```
docker model run hf.co/kaist-ai/mistral-orpo-alpha
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mistral-ORPO-⍺ (7B)

Mistral-ORPO is a fine-tuned version of mistralai/Mistral-7B-v0.1 using the odds ratio preference optimization (ORPO). With ORPO, the model directly learns the preference without the supervised fine-tuning warmup phase. Mistral-ORPO-⍺ is fine-tuned exclusively on HuggingFaceH4/ultrafeedback_binarized.

Github Repository: https://github.com/xfactlab/orpo

👍 Model Performance

1) AlpacaEval & MT-Bench

Model Name	Size	Align	MT-Bench	AlpacaEval 1.0	AlpacaEval 2.0
Mistral-`ORPO`-⍺	7B	`ORPO`	7.23	87.92	11.33
Mistral-`ORPO`-β	7B	`ORPO`	7.32	91.41	12.20
Zephyr β	7B	DPO	7.34	90.60	10.99
TULU-2-DPO	13B	DPO	7.00	89.5	10.12
Llama-2-Chat	7B	RLHF	6.27	71.37	4.96
Llama-2-Chat	13B	RLHF	6.65	81.09	7.70

2) IFEval

Model Type	Prompt-Strict	Prompt-Loose	Inst-Strict	Inst-Loose
Mistral-ORPO-⍺	0.5009	0.5083	0.5995	0.6163
Mistral-ORPO-β	0.5287	0.5564	0.6355	0.6619

🗺️ MT-Bench by Category

🖥️ Inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("kaist-ai/mistral-orpo-alpha")
tokenizer = AutoTokenizer.from_pretrained("kaist-ai/mistral-orpo-alpha")

# Apply chat template
query = [{'role': 'user', 'content': 'Hi! How are you doing?'}]
prompt = tokenizer.apply_chat_template(query, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors='pt')

# Generation with specific configurations
output = model.generate(
  **inputs,
  max_new_tokens=128,
  do_sample=True,
  temperature=0.7
)
response = tokenizer.batch_decode(output)

#<|user|>
#Hi! How are you doing?</s>
#<|assistant|>
#I'm doing well, thank you! How are you?</s>

📎 Citation

@misc{hong2024orpo,
      title={ORPO: Monolithic Preference Optimization without Reference Model}, 
      author={Jiwoo Hong and Noah Lee and James Thorne},
      year={2024},
      eprint={2403.07691},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}