Instructions to use Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3 with Transformers:

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

pipe = pipeline("text-generation", model="Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3")
model = AutoModelForCausalLM.from_pretrained("Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3")
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 Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3

SGLang

How to use Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3 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 "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3" \
    --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": "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3",
		"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 "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3" \
        --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": "Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3 with Docker Model Runner:
```
docker model run hf.co/Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3
```

MMPO_Gemma_7b_gamma1.1_epoch3

this is the model checkpoint for the paper:

Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback
Kyuyoung Kim*, Ah Jeong Seo*, Hao Liu, Jinwoo Shin, Kimin Lee
In EMNLP 2024 Findings

This model is a fine-tuned version of kykim0/gemma-7b-ultrachat-sft on the allenai/ultrafeedback_binarized_cleaned dataset.

The model is optimized with MMPO(Margin Matching Preference Optimization), which integrates per-feedback margin to enhance optimization. Specifically, given quality margins in pairwise preferences, MMPO utilizes soft target probabilities based on the Bradley-Terry model. You can find more details in the paper or the official code.

Evaluation results

For MT-Bench, this model shows a score of 7.53, which is higher than the score of 7.40 when trained with DPO:

For RewardBench, it achieves state-of-the-art performance compared to competing models at the same scale:

Training and evaluation data

Training: UltraFeedback
Evaluation: MT-Bench, RewardBench

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 64
optimizer: AdamW
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.3
mix_precision: bfloat16
num_epochs: 3

Downloads last month: 3

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3

Base model

google/gemma-7b

Finetuned

(366)

this model

Ahjeong
/

MMPO_Gemma_7b_gamma1.1_epoch3

MMPO_Gemma_7b_gamma1.1_epoch3

Evaluation results

Training and evaluation data

Training hyperparameters

Model tree for Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3

Dataset used to train Ahjeong/MMPO_Gemma_7b_gamma1.1_epoch3