Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 / model-00003-of-00012.safetensors

update Quark quantized Auto Mixed Precision (AMP) Llama-2-70b-chat-hf model with better accuracies (#2)

b7eaab4 verified about 2 months ago

4.96 GB

This file is stored with Xet . It is too big to display, but you can still download it.

( Raw pointer file )

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.