mit-han-lab / smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
https://arxiv.org/abs/2211.10438
MIT License
1.1k stars 127 forks source link

batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access. #43

Closed GuoYi0 closed 7 months ago

GuoYi0 commented 1 year ago

There is an error when running at this line of code: act_scales = torch.load('../act_scales/opt-13b.pt') _pickle.UnpicklingError: invalid load key, 'v'.

Guangxuan-Xiao commented 7 months ago

Hi,

Thank you for raising this issue! We have uploaded our activation scales on Huggingface.

Best, Guangxuan