facebookresearch / facebookresearch/SpinQuant
Performance on LLama2-7b model
Open
- Dominant language
- Python
- Stars
- 428
- Forks
- 93
- PR merge metrics
- No merged PRs in 30d
Description
Hi, I' would like to ask what might be the reason for small accuracy gain compared to naive Quarot approach in Llama-2-7b. Your table shows performance gain in llama3 based models. what might be the difference?
Contributor guide
Assessment
This issue has not been assessed yet.