支持自定义视觉编码器么（llava-llama3）?
Open
- Dominant language
- Python
- Stars
- 5.2k
- Forks
- 448
- Avg merge
- 3d 15h
- Merged PRs (30d)
- 26
Description
支持自定义视觉编码器么（llava-llama3）?
例如将clip换成siglip?
该如何实现？哪些代码需要修改？
Contributor guide
Research direction
Start by searching the repository for the llava-llama3 implementation and its CLIP integration points. Determine whether replacing CLIP with SigLIP is supported, which configuration or model components would need changes, and what validation would demonstrate that the custom visual encoder works.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100