FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[Original HTTPS Page]
AdityaLab/HAILS · GitHub
Uh oh!
There was an error while loading.
Please reload this page
.
AdityaLab
/
HAILS
Public
Notifications
You must be signed in to change notification settings
Fork
2
Star
8
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Branches
Tags
Open more actions menu
Latest commit
History
21 Commits
21 Commits
Folders and files
Name
Name
Last commit message
Last commit date
dataset/
M5
dataset/
M5
notebooks
notebooks
src
src
.gitignore
.gitignore
.python-version
.python-version
README.md
README.md
pretrainm5.py
pretrainm5.py
pyproject.toml
pyproject.toml
runm5.py
runm5.py
trainm5.py
trainm5.py
uv.lock
uv.lock
Repository files navigation
README
Hails
Instructions
Requirements:
Python >=3.11
uv
Installation
Download M5 Dataset following the instructions in
Reamde
Run ./dataset/M5/extract.sh
Run uv sync to download the required dependencies
Run uv run pretrainm5.py for pre-training (atleast for 10 ep)
Run rye run trainm5.py for training (atleast for 100 epochs)
Requires atleast 70 GB VRAM with Mixed precision
Toggle SCALE_PREC = False in trainm5.py to use FP16 to run on GPUs of less than 40 GB VRAM
About
No description or website provided.
Topics
hierarchical-time-series
pytorch
time-series-forecasting
Resources
Readme
Activity
Custom properties
Stars
8
stars
Watchers
0
watching
Forks
2
forks
Report repository
Releases
Packages
Used by
Contributors
Languages
Back
|
FazBrowse Home
|
New Git URL