InternLM / InternLM/InternLM-XComposer
About InternLM-XComposer-2.5-OmniLive
Open
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 175
- PR merge metrics
- No merged PRs in 30d
Description
想问问这个模型是如何微调的,论文没仔细写,只是说用了不同数据来微调不同的task的module,具体是怎么微调的,是分开微调还是一起微调用一起的数据呀?分开微调的话先调哪个呢?
压缩模块也没说具体用的哪些,不知道作者是否会给个详细讲解,是用的self-attention类似qformer的来压缩吗?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.