Limit the scale minimum value not to 0

intel / auto-round

Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

https://arxiv.org/abs/2309.05516

Apache License 2.0

200 stars 19 forks source link

Limit the scale minimum value not to 0 #209

Closed WeiweiZhang1 closed 1 month ago

WeiweiZhang1 commented 1 month ago

Limit the scale minimum value not to 0 tested on common models(>=10) currently, only effects Qwen2-57B-A14B-Instruct model