AttributeError: 'Attention' object has no attribute 'W_pack'

OpenGVLab / OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

MIT License

626 stars 49 forks source link

Open yrf200112 opened 7 months ago

yrf200112 commented 7 months ago

When quantized model occured this issue: AttributeError: 'Attention' object has no attribute 'W_pack'