amd
/

Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

Model card Files Files and versions

Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 / tokenizer.json

XuebinWang's picture

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

b7eaab4 verified 2 months ago

history contribute delete

3.62 MB

File too large to display, you can check the raw version instead.