An agentic coding and automation assistant, supporting both local and cloud LLMs.

Direct File

A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments

A small and simple HTML table parser not requiring any external dependency.

A curated list of awesome Green AI resources and tools to assess and reduce the environmental impacts of using and deploying AI.

Run ruff, isort, pyupgrade, mypy, pylint, flake8, and more on Jupyter Notebooks

Custom Tag component for streamlit

A collection of libraries to optimise AI model performances

Exploring finetuning public checkpoints on filter 8K sequences on Pile

A simple web app (Python/Flask) to summarize new papers from arXiv.org

stqdm is the simplest way to handle a progress bar in streamlit app.

Streamlit components that allow client side (javascript) to send data to the server side (python) and render HTML content without being processed by Markdown.

Open corpora and toolkit for assessing text readability in French (READI-LREC22)

Cache APT packages in GitHub Actions

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply

pepy is a site to get statistics information about any Python package.

Part of data repository for thesis/skripsi titled: "Assessment Study on ktrain Library for Text Processing"

Website for viewing database of Coronavirus research at CoronaCentral.ai

Machine learning to text-mine coronavirus research for CoronaCentral.ai

Finite-Interval Forecasting Engine: Machine learning models for discrete-time survival analysis and multivariate time series forecasting

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

CapsNet (from "Dynamic Routing Between Capsules") implemented in pytorch.

Text tokenization and sentence segmentation (segtok v2)