Qwen
/

Qwen2.5-VL-72B-Instruct-AWQ

Image-Text-to-Text

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

AWQ量化版损失有多大？可以再进行SFT微调吗？

#1

by HediZhao - opened 7 days ago

7 days ago

Qwen2.5-VL-72B-Instruct-AWQ 量化版相对原版损失有多大？有没有相关评测结论参考
AWQ可以再进行LoRA SFT吗？会不会导致误差进一步变大
有使用过的小伙伴，辛苦分享和指导~

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment