InternLM / InternLM/lmdeploy

LLaVA INT4 quantization

Open
#2,857 1 comment 0 reactions 1 assignee Claimed by @AllentDan View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

The performance of the LLaVA-1.5 13B model drops significantly after using 4-bit quantization. After turning on –search-scale, the performance still drops significantly.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.