16 Commits

Author	SHA1	Message	Date
Pratiyank Kumar	7c6911dce9	Merge 6bb22e0c15 into 88d6547df2	2025-04-08 22:12:19 +08:00
huxuedan	d29a967601	modify the explanation of MLA	2025-02-26 17:07:39 +08:00
Xingkai Yu	1398800ebf	fix scores mask	2025-02-14 20:26:45 +08:00
Pratiyank Kumar	6bb22e0c15	Merge branch 'main' into refactor/codebase	2025-02-08 09:14:14 +05:30
Xingkai Yu	5ee97a83f0	fix comment	2025-02-07 16:42:55 +08:00
Xingkai Yu	87a01053e4	Merge pull request #556 from XxAlonexX/main ... Fix Linear Layer Bias Initialization	2025-02-05 16:23:02 +08:00
XxAlonexX	6a30b43249	Fix Linear Layer Bias Initialization	2025-02-04 10:38:45 +05:30
pratiyankkumar	de7df86119	Refactored the codebase by defining seperate classes for different operations and implemented better type safety	2025-01-29 10:37:09 +05:30
Roman Fitzjalen	2756e130c2	clarify assertion error	2025-01-28 13:16:54 +01:00
pratiyankkumar	70ff909fdc	Refactored convert.py	2025-01-28 09:20:16 +05:30
enoch kan	bc77f22afc	Updated model.py docstrings	2025-01-05 18:24:31 +00:00
enoch kan	a1296f099e	Enhance documentation and update .gitignore for model conversion scripts	2025-01-05 18:18:18 +00:00
GeeeekExplorer	fd011c11aa	torch rmsnorm	2025-01-05 14:33:48 +08:00
Xingkai Yu	8710ec2ecb	require model-parallel in convert.py	2024-12-31 18:05:55 +08:00
Yang Wang	8f1c9488b5	handle missing scale_inv_name (#2) ... * handle missing scale_inv_name Fixed an issue where `weight` and `weight_scale_inv` (e.g. `model.layers.39.mlp.experts.92.gate_proj.weight` and `model.layers.39.mlp.experts.92.gate_proj.weight_scale_inv`) were not in the same SafeTensor, causing an assertion error due to scale_inv_name not being in the state_dict. * sort filename to reduce memory costs * Add CUDA cache clearing in memory management Added torch.cuda.empty_cache() to free up unused memory on the GPU,	2024-12-27 09:34:38 +08:00
stack-heap-overflow	4c2fdb8f55	Release DeepSeek-V3	2024-12-26 19:01:57 +08:00