CodingParadigm1
77c46698b9
added assert to Parser class
...
Parser now can apply assert to self
2025-02-03 10:24:23 -07:00
CodingParadigm1
c8146ec360
small patch
...
applied further Parser class
2025-02-03 10:18:58 -07:00
CodingParadigm1
267e7ba685
add functionality
...
- applied asyncio to more files
- added Parser class
- made small changes
2025-02-03 10:06:38 -07:00
CodingParadigm1
07de76f5ee
small patch
...
removed unnecessary variable
2025-02-02 06:14:17 -07:00
CodingParadigm1
35244be39f
moved dir calls
...
removed dir calls from for loops
2025-02-02 06:12:46 -07:00
CodingParadigm1
f2636dd366
updated async file reading
2025-02-02 03:55:47 -07:00
CodingParadigm1
1cb3e2a63f
reduced breaking changes
2025-02-02 03:49:23 -07:00
CodingParadigm1
60e3466ebf
Revert "optimized"
...
This reverts commit 3f5a2ebfc9
2025-02-02 03:04:15 -07:00
CodingParadigm1
3f5a2ebfc9
optimized
...
added parallel file processing, add faster tensor ops
2025-01-31 17:15:10 -07:00
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
