Hugging Face's logo

yifanzhang114
/
MM-RLHF-Reward-7B-llava-ov-qwen

Image-Text-to-Text
Transformers
Safetensors
llava_qwen
text-generation
conversational
Inference Endpoints
Model card Files Community
1
MM-RLHF-Reward-7B-llava-ov-qwen / README.md
yifanzhang114's picture
yifanzhang114
Update README.md
e4f86d5 verified
preview code
|
raw
history blame
1.61 kB
metadata
license: mit

The Next Step Forward in Multimodal LLM Alignment

[2025/02/10] 🔥 We are proud to open-source MM-RLHF, a comprehensive project for aligning Multimodal Large Language Models (MLLMs) with human preferences. This release includes:

  • A high-quality MLLM alignment dataset.
  • A strong Critique-Based MLLM reward model and its training algorithm.
  • A novel alignment algorithm MM-DPO.
  • Two new benchmarks.

Our dataset and algorithms enable consistent performance improvements across 10 dimensions and 27 benchmarks for open-source MLLMs.

Citation

If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX: