Modelpublic

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sdpo-gsm8k-debug_sdpo_quick-s43

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes

revisionmain step-00002 step-00001

file.gitattributes2 KBdownload

fileadapter_config.json1 KBdownload

fileadapter_model.safetensors160.1 MBdownload

filechat_template.jinja5 KBdownload

filemanifest.yaml3 KBdownload

fileoptimizer.pt320.4 MBdownload

fileREADME.md5 KBdownload

fileresolved_config.yaml2 KBdownload

filerng_state.pth14 KBdownload

filescheduler.pt1 KBdownload

filetokenizer_config.json354 Bdownload

filetokenizer.json16.4 MBdownload

filetrainer_state.json1 KBdownload

filetraining_args.bin7 KBdownload

amr-fma/amr-fma-Llama-3.1-8B-Instruct-lora_sdpo-gsm8k-debug_sdpo_quick-s43 · step-00001 · files are served by the source, never re-hosted here