AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies
Paper
•
2408.06567
•
Published
•
2
•
1
Guang Liu
ZacLiu
AI & ML interests
None yet
Recent Activity
new activity
15 days ago
BAAI/Infinity-Instruct:为什么3M，7M的label字段值都是空的
updated
a model
about 1 month ago
BAAI/Aquila-VL-2B-llava-qwen
updated
a collection
about 2 months ago
Aquila
Organizations
ZacLiu's activity
为什么3M，7M的label字段值都是空的
4
#26 opened about 1 month ago
by
codingling
Decontamination?
1
#20 opened 4 months ago
by
alpayariyak
0729聊天数据集有计划开源吗？
2
#16 opened 5 months ago
by
yixinsong
commented
a
paper
5 months ago
Different dataset versions ? 3M / 0608 / 06012
9
#4 opened 7 months ago
by
philschmid
Language field
1
#5 opened 6 months ago
by
Tijmen2
Did you dedupe this???
2
#3 opened 7 months ago
by
rombodawg
Update README.md
1
#1 opened 7 months ago
by
sjcfr
Update pytorch_model.bin.index.json
1
#2 opened about 1 year ago
by
Leymore
(Possible) Inconsistencies in model files
4
#1 opened about 1 year ago
by
Vermilion3154
非常感谢BAAI的开源项目，发现语料库的一点小问题
1
#3 opened about 1 year ago
by
ishotoli
请问有gptq或者gguf版本吗
1
#4 opened about 1 year ago
by
Lenosey
When will base model release?
#2 opened about 1 year ago
by
lucasjin
Fix deprecated float16/fp16 variant loading through new `version` API.
#12 opened over 1 year ago
by
patrickvonplaten
Could you have any plans to offer a version based on stable diffusion 2.1?
1
#3 opened about 2 years ago
by
0xDing
训练使用的句子长度
5
#2 opened about 2 years ago
by
junnyu
Enable inference widget
#1 opened about 2 years ago
by
valhalla
Update app.py
#1 opened about 2 years ago
by
ZacLiu