search

Cornell-RelaxML / QuIP

Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
345 stars 32 forks source link

support for llama #8

Closed Ottovonxu closed 1 year ago

Ottovonxu commented 1 year ago

Hi

May I ask if there is an update regarding the QuIP quantization of Llama?

Thanks a lot!

jerry-chee commented 1 year ago

yes, we will post an update shortly to reproduce experiments from the final version of the neurips23 paper