2
1
0
A new method was able to delete 40% of LLM layers with no drop in accuracy.
This makes them mich cheaper and faster.
The method combines pruning, quantization and PEFT.
They tested this across various open source models.
Each family of models had a maximum amount of layers…
时政
(
twitter.com
)
由
Lior⚡
提交
A new method was able to delete 40% of LLM layers with no drop in accuracy.
This makes them mich cheaper and faster.
The method combines pruning, quantization and PEFT.
They tested this across various open source models.
Each family of models had a maximum amount of layers that could be deleted before accuracy dropped:
- Mistral - 30%
- Lama 70B - 40%
- Llama 13B - 50%
Great paper.
点击图片查看原图
Markdown支持
评论加载中...
您可能感兴趣的：
更多
2
2
1
1
3
2
1
1
4
2
1
1
7
2
1
1
8
2
1
1
9
2
1
1
