1308 位用户此时在线
24小时点击排行 Top 10：
- 本站自动实时分享网络热点
- 24小时实时更新
- 所有言论不代表本站态度
- 欢迎对信息踊跃评论评分
- 评分越高，信息越新，排列越靠前
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
1
2
1
1
2
2
1
1
3
2
1
1
4
6
5
5
5
2
1
1
6
2
1
1
7
2
1
1
8
2
1
1
9
2
1
1
10
2
1
1
11
2
1
1
12
2
1
1
13
2
1
1
14
2
1
1
15
2
1
1
16
2
1
1
17
2
1
1
18
2
1
1
19
3
2
2
20
2
1
1
21
2
1
1
22
2
1
1
23
That wasn’t hesitation. It was a moment of visible disbelief.
2
1
1
That wasn’t hesitation. It was a moment of visible disbelief.
The spokesperson gives a brief pause and a knowing look.
Context: A reporter claims China can destroy U.S. weapons before they reach Taiwan.
That expression comes before the official response.
Sometimes the pause is
时政
(
twitter.com)
00:00:51
24
Chinese wumao accounts are at it again. This is exactly why accurate translation matters.
2
1
1
Chinese wumao accounts are at it again. This is exactly why accurate translation matters.
In this case, a video of a foreign person speaking a language most viewers do not understand was reposted with a completely unrelated political caption. Because viewers cannot verify the
时政
(
twitter.com)
00:00:39