Hugging Face's logo

Anthonyg5005
/
hf-scripts

English
Model card Files Community
1
hf-scripts / README.md
Anthonyg5005's picture
Anthonyg5005
Update README.md
ff3850b
preview code
|
raw
history blame
3.58 kB
metadata
license: agpl-3.0
language:
  - en

scripts

Personal scripts to automate some tasks.
Will try to keep external module use to a minimum, other than huggingface_hub.
Feel free to send in PRs or use this code however you'd like.
GitHub mirror

For GitHub: Would recommend creating pull requests and discussions on the offical huggingface repo

existing files

work in progress/not tested (unfinished branch)

  • Auto exl2 upload script
    • Will create repo and create a specified number of custom quants on individual branches
    • Windows/Linux support

other recommended stuff

usage

  • Manage branches

    • Run script and follow prompts. You will be required to be logged in to HF Hub. If you are not logged in, you will need a WRITE token. You can get one in your HuggingFace settings. May get some updates in the future for handling more situations. All active updates will be on the unfinished branch. Colab and Kaggle keys are supported.

  • EXL2 Single Quant

    • Allows you to quantize to exl2 using colab. This version creates a exl2 quant to upload to private repo. Should work on any Linux jupyterlab server with CUDA, ROCM should be supported by exl2 but not tested. Only 7B tested on colab.

  • EXL2 Local Quant Windows

    • Easily creates environment to quantize models to exl2 using Windows to your local machine.

  • Upload folder to repo

    • Uploads user specified folder to specified repo, can create private repos too. Not the same as git commit and push, instead uploads any additional files.

  • Download models

    • Make sure you have huggingface_hub installed as it has the same dependencies. You can install it with 'pip install huggingface-hub'. To use the script, open a terminal and run 'python download-model.py USER/MODEL:BRANCH'. There's also a '--help' flag to show the available arguments. To download from private repositories, make sure to login using 'huggingface-cli login' or (not recommended) HF_TOKEN environment variable.

extras

  • HF login snippet
    • The login method that I wrote to make fetching the token better.
  • HF login snippet kaggle
    • Same as above but for cloud ipynb environments like Colab and Kaggle (Kaggle secret support)