Skip to content

H0D1N/Model-Generation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Model-Generation

The code for flexible model generation

Use the Colossal-AI for training

start training with

colossalai run --nproc_per_node 4 train.py

Using EMA for trainning

colossalai run --nproc_per_node 4 train.py --model_ema --world_size 4

Problem

In config.py, Gradient Clipping is not working,so I comment out

#clip_grad_norm = 1.0

Gate Selection Network

6211679574347_.pic.jpg

About

The code for flexible model generation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages