metadata

license: llama2
language:
  - en
base_model:
  - liuhaotian/llava-v1.5-7b
tags:
  - reward-model
  - reward_model

Align²LLaVA Answer Reward Model

Welcome to the model card for Align²LLaVA Answer Reward Model. This model is implemented based on LLaVA-1.5-7B. In this repo, we provide the LoRA delta checkpoint for our answer reward model.

For detailed imformation, please visit our GitHub repository.

Align2LLaVA Answer Reward Model

Align²LLaVA Answer Reward Model