Modelpublic

nm-testing/Meta-Llama-3-8B-Instruct-FP8-channel-output-activation-kv_cache-qkv_proj

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes7downloads

file.gitattributes2 KBdownload

fileconfig.json7 KBdownload

filegeneration_config.json194 Bdownload

filemodel-00001-of-00004.safetensors4.59 GBdownload

filemodel-00002-of-00004.safetensors4.59 GBdownload

filemodel-00003-of-00004.safetensors4.05 GBdownload

filemodel-00004-of-00004.safetensors1002.0 MBdownload

filemodel.safetensors.index.json45 KBdownload

filerecipe.yaml462 Bdownload

filespecial_tokens_map.json296 Bdownload

filetokenizer_config.json50 KBdownload

filetokenizer.json16.4 MBdownload

nm-testing/Meta-Llama-3-8B-Instruct-FP8-channel-output-activation-kv_cache-qkv_proj · main · files are served by the source, never re-hosted here