lczerolens

🔬 Interpretability for Leela Chess Zero networks.

https://github.com/xmaster6y/lczerolens

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (13.1%) to scientific vocabulary

Keywords

chess lc0 xai

Last synced: 6 months ago · JSON representation ·

Repository

🔬 Interpretability for Leela Chess Zero networks.

Basic Info

Host: GitHub
Owner: Xmaster6y
License: mit
Language: Python
Default Branch: main
Homepage: https://lczerolens.readthedocs.io
Size: 1.66 MB

Statistics

Stars: 15
Watchers: 5
Forks: 3
Open Issues: 10
Releases: 10

Topics

chess lc0 xai

Created about 2 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Citation

lczerolens 🔍

Leela Chess Zero (lc0) Lens (lczerolens): a set of utilities to make interpretability easy and framework-agnostic (PyTorch): use it with tdhook, captum, zennit, or nnsight.

Getting Started

Installs

bash pip install lczerolens

Take the viz extra to render heatmaps and the backends extra to use the lc0 backends.

Run Models

Get the best move predicted by a model:

```python from lczerolens import LczeroBoard, LczeroModel

model = LczeroModel.from_hf("lczerolens/maia-1100") board = LczeroBoard()

output = model(board) bestmoveidx = output["policy"].argmax() print(board.decodemove(bestmove_idx)) ```

Framework-Agnostic Interpretability

Use lczerolens with your preferred PyTorch interpretability framework (tdhook, captum, zennit, nnsight). More examples in the framework-agnostic interpretability notebook.

```python from lczerolens import LczeroBoard, LczeroModel model = LczeroModel.from_hf("lczerolens/maia-1100") board = LczeroBoard()

TODO: complete this example

```

Features

Tutorials

Demo

Spaces

Some Hugging Face Spaces are available to try out the library. The demo (:red_circle: in construction) will showcase some of the features of the library and the backends demo makes the conversion of lc0 models to onnx easy.

Local Demo

Additionally, you can run the gradio demos locally. First you'll need to clone the spaces (after cloning the repo):

bash git clone https://huggingface.co/spaces/lczerolens/demo spaces/demo

And optionally the backends demo:

bash git clone https://huggingface.co/spaces/lczerolens/backends-demo spaces/backends-demo

And then launch the demo (running on port 8000):

bash just demo

To test the backends use:

bash just demo-backends

Full Documentation

See the full documentation.

Contribute

See the guidelines in CONTRIBUTING.md.

Owner

Name: Yoann Poupart
Login: Xmaster6y
Kind: user
Location: Lyon
Company: ENS de Lyon

Website: https://perso.ens-lyon.fr/yoann.poupart/
Repositories: 3
Profile: https://github.com/Xmaster6y

:computer: Self-taught and tech-savvy student.

Citation (CITATION.cff)

cff-version: 1.2.0
title: LCZeroLens
version: 0.1.0
date-released: 2024-02-09
type: software
authors:
  - name: Yoann Poupart
repository-code: 'https://github.com/Xmaster6y/lczerolens'
repository-artifact: 'https://github.com/Xmaster6y/lczerolens/releases/'
keywords:
  - chess
  - explainable AI (XAI)
license: MIT

GitHub Events

Total

Create event: 46
Release event: 6
Issues event: 39
Watch event: 9
Delete event: 43
Issue comment event: 60
Push event: 161
Pull request review event: 59
Pull request review comment event: 90
Pull request event: 79
Fork event: 1

Last Year

Create event: 46
Release event: 6
Issues event: 39
Watch event: 9
Delete event: 43
Issue comment event: 60
Push event: 161
Pull request review event: 59
Pull request review comment event: 90
Pull request event: 79
Fork event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 33
Total pull requests: 65
Average time to close issues: about 1 month
Average time to close pull requests: 5 days
Total issue authors: 1
Total pull request authors: 2
Average comments per issue: 0.18
Average comments per pull request: 0.94
Merged pull requests: 53
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 22
Pull requests: 40
Average time to close issues: 4 days
Average time to close pull requests: about 5 hours
Issue authors: 1
Pull request authors: 2
Average comments per issue: 0.27
Average comments per pull request: 1.25
Merged pull requests: 33
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

Xmaster6y (33)

Pull Request Authors

Xmaster6y (62)
NOVAdrien (3)

Top Labels

Issue Labels

feature (5) other (4) roadmap (2) bug (1)

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- pypi 406 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 8
Total maintainers: 1

pypi.org: lczerolens

Interpretability for LeelaChessZero networks.

Documentation: https://lczerolens.readthedocs.io/
License: mit
Latest release: 0.3.3
published 10 months ago

Versions: 8
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 406 Last month

Rankings

Dependent packages count: 9.9%

Average: 37.7%

Dependent repos count: 65.5%

Maintainers (1)

Xmaster6y