Modelpublic

cutelemonlili/Qwen2.5-0.5B-Instruct_MATH_training_sdft_response_Qwen2.5_0.5B_only_right

sourceHugging Faceotherupdated 2y agoView on Hugging Face

0likes17downloads

file.gitattributes2 KBdownload

fileadded_tokens.json605 Bdownload

fileall_results.json342 Bdownload

fileconfig.json732 Bdownload

fileeval_results.json160 Bdownload

filegeneration_config.json242 Bdownload

filemerges.txt1.6 MBdownload

filemodel.safetensors942.3 MBdownload

fileREADME.md2 KBdownload

filespecial_tokens_map.json613 Bdownload

filetokenizer_config.json7 KBdownload

filetokenizer.json10.9 MBdownload

filetrain_results.json202 Bdownload

filetrainer_log.jsonl81 KBdownload

filetrainer_state.json73 KBdownload

filetraining_args.bin7 KBdownload

filetraining_eval_loss.png42 KBdownload

filetraining_loss.png44 KBdownload

filevocab.json2.6 MBdownload

cutelemonlili/Qwen2.5-0.5B-Instruct_MATH_training_sdft_response_Qwen2.5_0.5B_only_right · main · files are served by the source, never re-hosted here