open-compass / open-compass/VLMEvalKit
怎样对llava codebase微调得到的lora模型进行评测？
Open
@kennymckormick is already working on this.
Since Apr 7, 2025.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 768
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 17
Description
请问使用https://github.com/haotian-liu/LLaVA/ 框架微调得到的lora模型，应该怎么进行评测呢？
我看到https://github.com/haotian-liu/LLaVA/ 这个仓库里面有https://github.com/haotian-liu/LLaVA/blob/main/scripts/merge_lora_weights.py 支持合并的权重，但是这个权重和https://huggingface.co/liuhaotian/llava-v1.5-7b 的形式不太一样，huggingface中没有打包vision encoder的权重，而使用上述代码得到的权重会包括vision tower的权重，这个问题怎么能优雅地解决呢？vlmevalkit中llava的示例似乎是希望一个huggingface格式的权重。谢谢
huggingface中没有打包vision部分权重
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.