ruikangliu / FlatQuant

Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization
MIT License
25 stars 3 forks source link

Request for Quantized Model Availability #4

Open JoesSattes opened 3 days ago

JoesSattes commented 3 days ago

Thank you for the impressive work! On consumer GPUs, it’s tough to run larger models without quantization. Could you please provide quantized versions (7B, 70B)? Sharing these on Hugging Face would be greatly appreciated.