intern2.5-20B微调 后词表长度不一致
Open
- Dominant language
- Python
- Stars
- 5.2k
- Forks
- 448
- Avg merge
- 3d 15h
- Merged PRs (30d)
- 26
Description
您好，intern2.5-20B微调合并后出现了added_tokens.json，转换gguf模型的时候是成功的，加载的时候显示tensor 'token_embd.weight' has wrong shape; expected 6144, 92550, got 6144, 92544，好像是词表长度不一致，请问怎么办？
Contributor guide
Assessment
This issue has not been assessed yet.