vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update: change order

Browse source
This commit is contained in:
Trần Đức Nam 2023-12-14 16:31:19 +07:00
parent 2ea3934ec3
commit 8a3ceced04
3 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
awqutils/README.md → examples/awqutils/README.md
View file

@ -60,7 +60,7 @@ Several quantization methods are supported. They differ in the resulting model d
|Llama 7B | ms/tok @ 4th | xxx | xx | xx | xx |
|Llama 7B | ms/tok @ 8th | xxx | xx | xx | xx |
|Llama 7B | bits/weight | 16.0 | 4.5 | 5.0 | 2.6 |
|AWQ-LLama 7B| perplexity | 5.9175 | 6.0252 | xxxxxx | xxxxx |
|AWQ-LLama 7B| perplexity | 5.9175 | 6.0252 | 5.9987 | xxxxx |
|AWQ-LLama 7B| file size | 12.9G | 3.5G | 3.9G | 2.7G |
|AWQ-LLama 7B| ms/tok @ 4th | xxx| xxx | xxx | xxx |
|AWQ-LLama 7B| ms/tok @ 8th | xxx| xx | xx | xx |

0
awqutils/apply_awq.py → examples/awqutils/apply_awq.py
View file

0
awqutils/requirements.txt → examples/awqutils/requirements.txt
View file