1274 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
2
1
1
5
2
1
1
6
3
2
2
7
A new video compilation recorded by a young woman shows how quickly the music festival in Israel went from a good party to fight for survival.
2
1
1
A new video compilation recorded by a young woman shows how quickly the music festival in Israel went from a good party to fight for survival.
After a while, Israeli police officer and a tank show up to protect the young festival goers, but they come under heave fire from Hamas
时政
(
twitter.com)
00:02:55
8
DeepSeek dropped a new model on a Saturday. Markets don't open until Monday.
2
1
1
DeepSeek dropped a new model on a Saturday. Markets don't open until Monday.
The last time DeepSeek owned a weekend, Nvidia lost about $590 billion the next session. Down 17% in a day.
This time it's V4.1 Flash-1017. Their launch post did 465K views and 900+ quotes in a few
时政
(
twitter.com)
00:00:30
9
2
1
1
10
2
1
1
11
3
2
2
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
2
1
1
20
2
1
1
21
2
1
1
22
2
1
1
23
2
1
1
24
2
1
1