InternLM / InternLM/InternLM-XComposer
Script for quantizing models
Open
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 175
- PR merge metrics
- No merged PRs in 30d
Description
I am trying to quantize internlm-xcomposer2-vl-1_8b using AutoGTPQ, but I am running into non-trivial errors. So, was wondering if you could share the script that you used for quantizing internlm-xcomposer2-vl-7b in 4 bit. TIA!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.