ByungKwanLee/MoAI
[ECCV 2024] Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks.
PythonMIT
Issues
- 13
- 1
questions about training
#22 opened by cassiaaaaaa - 2
- 3
question about mix-precision in training
#19 opened by cassiaaaaaa - 6
Lora analogy
#20 opened by YasserdahouML - 4
Train code, architecture, and training cost?
#4 opened by zmj1203 - 4
question about prompt in training
#18 opened by cassiaaaaaa - 23
The training process detail
#12 opened by lucasjinreal - 0
A closed question
#17 opened by cassiaaaaaa - 1
- 1
About the 'Word Embed', how did you get it?
#15 opened by cassiaaaaaa - 2
- 6
How many GPU RAMs to inference?
#8 opened by phuchm - 1
question about LLM and data
#11 opened by JiuhaiChen - 1
It is Amazing!
#1 opened by atazangene - 2
Why is the inference speed so slow?
#3 opened by khiemkhanh98 - 11
cant build detectron2 module on windows
#10 opened by sneccc - 1
Does it support multi images input?
#9 opened by xiaodangao137 - 1
Incompatible with CUDA version (12.3)
#7 opened by phuchm - 1