CoolFace
Modelpublic

amd/Llama-2-70b-chat-hf-WMXFP4-AMXFP4-KVFP8-Scale-UINT8-MLPerf-GPTQ

sourceHugging Facellama2updated 1y agoView on Hugging Face
0likes12downloads
root
file.gitattributes2 KBdownload
fileconfig.json9 KBdownload
filegeneration_config.json183 Bdownload
fileLICENSE.txt7 KBdownload
filemodel-00001-of-00008.safetensors4.61 GBdownload
filemodel-00002-of-00008.safetensors4.65 GBdownload
filemodel-00003-of-00008.safetensors4.55 GBdownload
filemodel-00004-of-00008.safetensors4.65 GBdownload
filemodel-00005-of-00008.safetensors4.55 GBdownload
filemodel-00006-of-00008.safetensors4.66 GBdownload
filemodel-00007-of-00008.safetensors4.63 GBdownload
filemodel-00008-of-00008.safetensors2.56 GBdownload
filemodel.safetensors.index.json120 KBdownload
fileNOTICE111 Bdownload
fileREADME.md3 KBdownload
fileResponsible-Use-Guide.pdf1.2 MBdownload
filespecial_tokens_map.json437 Bdownload
filetokenizer_config.json2 KBdownload
filetokenizer.model488 KBdownload
fileUSE_POLICY.md5 KBdownload

amd/Llama-2-70b-chat-hf-WMXFP4-AMXFP4-KVFP8-Scale-UINT8-MLPerf-GPTQ · main · files are served by the source, never re-hosted here