issues
search
SHI-Labs
/
CuMo
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Apache License 2.0
117
stars
8
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Is MOE used for LLM?
#12
dana-niu
opened
6 days ago
1
power usage is low.
#11
Marcovaldon
opened
3 weeks ago
2
Model checkpoints
#10
chricro
closed
3 weeks ago
2
NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.
#9
efraim-evo
closed
2 weeks ago
7
NameError: name 'LlavaMixtralForCausalLM' is not defined
#8
makemecker
closed
4 weeks ago
2
Missing llava Directory for Training Script Execution
#7
makemecker
closed
1 month ago
1
Error when loading the saved checkpoint.
#6
Marcovaldon
closed
1 month ago
1
Train the model without Deepspeed ZeRO
#5
MOSHIIUR
closed
1 month ago
3
support Llama-3 models
#4
chricro
closed
1 month ago
1
Is there any inference framwork to accelerate CuMo?
#3
leoozy
closed
1 month ago
3
What the size of the input image should be of CuMo?
#2
leoozy
closed
1 month ago
5
NameError: name 'LlavaMixtralForCausalLM' is not defined
#1
leoozy
closed
1 month ago
1