fix(v8): S1 lora vocab sync, M1 test_sbla tuple unpack, N1 dead code removal 36e31c4
zhan1206 commited on
Spaces:
Running
Running
Commit History
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
fix: v5 remove empty tokenizer.json, unify think tokens, integrate tokenizer into training pipeline bae07a4
zhan1206 commited on
feat: train SentencePiece tokenizer + update README ff4d952
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: M2/S2/S4/M4 defect repairs a3aa0f2
zhan1206 commited on
fix: v3 comprehensive defect repair 3ab86b9
zhan1206 commited on
chore: 添加 Windows 保留名到 .gitignore（避免 NUL 等文件被追踪） 201e778
zhan1206 commited on
feat: 重写 DyQuant 量化代码，修复 thinking_dial.py 编码问题 95a02a4
zhan1206 commited on
fix: 修复 S1-S4/M2-M4 缺陷，规范化工程结构 03059b7
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