mit-han-lab / smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Home Page:https://arxiv.org/abs/2211.10438

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Support for LLAMA

fmac2000 opened this issue · comments

Hi Authors,

Are you planning on supporting LLAMA in smoothquant when it hits the market? - I've always liked working with your projects and find LLAMA to be the next evolution of LLMs.

Thank you!

commented

Hi, we are currently waiting for access to LLaMA models. We do plan to test our method on the new models :)

🚂 All Aboard! 🚂

Thanks for the good news! I'll keep an eye out