fusion-llm-demo / train /dpo_finetune.py

Commit History

fix: v5 remove empty tokenizer.json, unify think tokens, integrate tokenizer into training pipeline
bae07a4

zhan1206 commited on

fix: v4 comprehensive defect repair (S3/M1/M3/M4/M5/F2/F3)
20a50dc

zhan1206 commited on

feat: M4 attention unification + DPO trainer + inference dashboard
e5984c7

zhan1206 commited on