Shaw
|
0daf7051fc
Update quantization.md
|
3 years ago |
Shaw
|
d405d89c87
Update README.md
|
3 years ago |
Sengxian
|
28e449b79f
Update quantization docs and scripts
|
3 years ago |
Sengxian
|
6b410ef9d2
Add checkpoint tensor parallel conversion script
|
3 years ago |
Zhengxiao Du
|
7be5ba1758
Fix finalize in BeamSearchStrategy
|
3 years ago |
Zhengxiao Du
|
3bb0f456d1
Fix top_p argument in generate.py
|
3 years ago |
Zhengxiao Du
|
1241f03ec2
Fix sampling in BaseStrategy
|
3 years ago |
Shaw
|
a7a1bfb806
Update README.md
|
3 years ago |
Shaw
|
4c5be1093d
Create README.md
|
3 years ago |
Zhengxiao Du
|
26543554f8
Remove redundant imports
|
3 years ago |
Zhengxiao Du
|
10677a8dc2
Fix consider_end
|
3 years ago |
Zhengxiao Du
|
e7d58c7d9d
Fix generate.py
|
3 years ago |
Sengxian
|
113f5f1364
Add language modeling task
|
3 years ago |
Sengxian
|
c64d6ea33c
Fix quantization argument bug
|
3 years ago |
Zhengxiao Du
|
223c40b636
Fix BeamSeachStartegy
|
3 years ago |
Sengxian
|
21cadf7677
Add load from quantized checkpoint
|
3 years ago |
Zhengxiao Du
|
bb9fbe4bfc
Implement batch generation
|
3 years ago |
Sengxian
|
96eac9f33b
Add 4-bit quantization and CUDA kernels
|
3 years ago |
Sengxian
|
e10b098020
Add 8-bit quantization
|
3 years ago |
Shaw
|
5b1b0bf8ca
Update README_zh.md
|
3 years ago |
Aohan Zeng
|
a8a1d5818b
Merge pull request #7 from erjanmx/fix-readme-typo
|
3 years ago |
Erjan Kalybek
|
738695c6c9
Fix readme typo
|
3 years ago |
Shaw
|
11befcbf80
Fix script name in README
|
3 years ago |
xiao9905
|
22d1a03c3e
Merge branch 'main' of github.com:THUDM/GLM-130B into main
|
3 years ago |
xiao9905
|
964695129f
update English version of the training logs
|
3 years ago |
Sengxian
|
20c0a9eca2
Fix script name in README
|
3 years ago |
Shaw
|
0aefc909ba
Fold acknowledgement list
|
3 years ago |
Shaw
|
63298822e7
Fold acknowledge list
|
3 years ago |
Shaw
|
d4a1738503
Fold acknowledgement list
|
3 years ago |
Shaw
|
0bf31162bf
Fold acknowledgement list
|
3 years ago |