Instructions to use UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 with Transformers:

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

pipe = pipeline("text-generation", model="UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2")
model = AutoModelForCausalLM.from_pretrained("UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2")
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 UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2

SGLang

How to use UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 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 "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2" \
    --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": "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2",
		"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 "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2" \
        --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": "UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2 with Docker Model Runner:
```
docker model run hf.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)

Mistral7B-PairRM-SPPO-Iter2

This model was developed using Self-Play Preference Optimization at iteration 2, based on the mistralai/Mistral-7B-Instruct-v0.2 architecture as starting point. We utilized the prompt sets from the openbmb/UltraFeedback dataset, splited to 3 parts for 3 iterations by snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset. All responses used are synthetic.

This is the model reported in the paper , with K=5 (generate 5 responses per iteration). We attached the Arena-Hard eval results in this model page.

Links to Other Models

Model Description

Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets.
Language(s) (NLP): Primarily English
License: Apache-2.0
Finetuned from model: mistralai/Mistral-7B-Instruct-v0.2

AlpacaEval Leaderboard Evaluation Results

Model	LC. Win Rate	Win Rate	Avg. Length
Mistral7B-PairRM-SPPO Iter 1	24.79	23.51	1855
Mistral7B-PairRM-SPPO Iter 2	26.89	27.62	2019
Mistral7B-PairRM-SPPO Iter 3	28.53	31.02	2163
Mistral7B-PairRM-SPPO Iter 1 (best-of-16)	28.71	27.77	1901
Mistral7B-PairRM-SPPO Iter 2 (best-of-16)	31.23	32.12	2035
Mistral7B-PairRM-SPPO Iter 3 (best-of-16)	32.13	34.94	2174

Arena-Hard Evaluation Results

Model	Score	95% CI	average # Tokens
Mistral7B-PairRM-SPPO-Iter3	23.3	(-1.8, 1.8)	578

Open LLM Leaderboard Evaluation Results

Results are reported by using lm-evaluation-harness v0.4.1

	arc_challenge	truthfulqa_mc2	winogrande	gsm8k	hellaswag	mmlu	average
Mistral7B-PairRM-SPPO Iter 1	65.02	69.4	77.82	43.82	85.11	58.84	66.67
Mistral7B-PairRM-SPPO Iter 2	65.53	69.55	77.03	44.35	85.29	58.72	66.75
Mistral7B-PairRM-SPPO Iter 3	65.36	69.97	76.8	42.68	85.16	58.45	66.4

MT-Bench Evaluation Results

	1st Turn	2nd Turn	Average
Mistral7B-PairRM-SPPO Iter 1	7.63	6.79	7.21
Mistral7B-PairRM-SPPO Iter 2	7.90	7.08	7.49
Mistral7B-PairRM-SPPO Iter 3	7.84	7.34	7.59

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
eta: 1000
per_device_train_batch_size: 8
gradient_accumulation_steps: 1
seed: 42
distributed_type: deepspeed_zero3
num_devices: 8
optimizer: RMSProp
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_train_epochs: 18.0 (stop at epoch=1.0)

Citation

@misc{wu2024self,
      title={Self-Play Preference Optimization for Language Model Alignment}, 
      author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan},
      year={2024},
      eprint={2405.00675},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}