v18: fix N18/N19/N20/N21/N22 Thinking Dial pipeline bugs 47aafb2
zhan1206 commited on
Spaces:
Running
Running
Commit History
v17: fix Thinking Dial training pipeline (N10/N11/N12/N13/N14/N15/N16/N17) 2e32205
zhan1206 commited on
v16: fix critical audit defects (N6/N7/N8/N9 + S3/S4/M2/M5) 65bdd96
zhan1206 commited on
v15: fix remaining audit issues (F1/F2/S1/M3/M8/doc) 2c578a9
zhan1206 commited on
v14 fix: F1 ThinkingDialModel thinking_embedding/gate 实际使用，F5 top_p NaN guard，M1 RoPE position_ids，M6 position_ids 传递链，DPO tokenizer 属性，forward() position_ids 参数 c1899e9
zhan1206 commited on
fix: comprehensive audit fixes - CRITICAL/HIGH/MEDIUM/LOW a959e9a
zhan1206 commited on
fix: v6 audit - all critical/severe/moderate/minor defects 1c801e3
zhan1206 commited on
feat: implement S1 KV Cache + S2 GQA in SBLAttention 93c5166
zhan1206 commited on
fix: F1 mask double-conversion NaN, F2 think token old format, S3 vocab sync, S1/S2 TODO, N1-N5 4cfb0d8
zhan1206 commited on
chore: replace author real name with GitHub username 17159b7
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
fix: v3 comprehensive defect repair 3ab86b9
zhan1206 commited on
fix: FusionModel forward propagation loss=NaN fdb1083
zhan1206 commited on
feat: 完成 SBLA 注意力集成 + MVP 训练流程 c77cab5
zhan1206 commited on
feat: 初始化 Fusion 项目 - 六边形开源大模型 22cd791
zhan1206 commited on