Increasing throughput with batches and quantization
pinned 7
#11 opened over 2 years ago
by 
miguelcarv
new dependencies
#23 opened over 1 year ago
by 
hincalt
Torchvision error
👀➕ 2
1
#22 opened over 1 year ago
by 
Saidur49
Breaks with quantization in newer transformers revisions (fix included)
👍 2
1
#21 opened about 2 years ago
by 
panopstor
Update modeling_cogvlm.py
#19 opened about 2 years ago
by 
nielsr
How to Encode Inputs for Supervised Fine-tuning of CogVLM
👍 1
1
#17 opened over 2 years ago
by 
ayensujeremiah
noob: Can we use RAG to improve cogagent/cogvlm performance
3
#16 opened over 2 years ago
by 
anothercoder2
Stunningly good
#13 opened over 2 years ago
by 
cmp-nct
Guidance on How to Train / Finetune Model
👍 1
13
#6 opened over 2 years ago
by 
mnbucher