amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 download history

amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 is a 54.6B-parameter model model by amd. In the last 30 days it was downloaded 103 times (21 in the last 7 days), and 545 times in total.

It ranks #184,943 on the Hub by monthly downloads.

It has 0 likes.

It is a quantization of meta-llama/Llama-2-70b-chat-hf.

Open amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 on Hugging Face