s444415/donut
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
70 Commits 2 Branches 0 Tags 456 KiB
Jupyter Notebook 76.1%
Python 23.9%
master
Go to file
s444415 d3cce99c85 streaming training, from zero configuration
2023-03-24 11:47:10 +00:00
notepads streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
old new training script with config, files split 2023-01-04 11:10:24 +01:00
utils working streaming training 2023-03-17 15:18:40 +01:00
.gitignore streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
config-eval.yaml streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
config-train.yaml streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
eval.py streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
README.md readme 2023-01-10 18:29:00 +01:00
requirements.txt gitignore, reqs, train_stream test 2023-03-14 21:43:21 +00:00
train_stream.py streaming training, from zero configuration 2023-03-24 11:47:10 +00:00
train.py restore donut 2023-01-25 17:44:25 +01:00

README.md

Donut script for train and eval

Instalation/setup:

-> pip install -r requirements.txt -> export HUG_TOKEN=YourToken - token needed for pushing model to huggingface after training

Usage:

Train

-> python train --config config-train.yaml

Evaluation

-> python eval --config config-eval.yaml

Configuration

Need to suply config file like config-eval.yaml for evaluation or config-train.yaml for traning