Lists (3)
Starred repositories
Ongoing research training transformer models at scale
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
📬 A knowledge graph querying framework for JavaScript
Various utilities for processing the data.
Universal Dependencies online documentation
Common Voice is part of Mozilla's initiative to help teach machines how real people speak.
Streamlit — A faster way to build and share data apps.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
A library for efficient similarity search and clustering of dense vectors.
Javascript Virtual Keyboard - Customizable, responsive and lightweight
Unsupervised text tokenizer for Neural Network-based text generation.
Style and Grammar Checker for 25+ Languages
Graphical Java application for managing BibTeX and BibLaTeX (.bib) databases
Open standard for machine learning interoperability
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
Google Research
Flax is a neural network library for JAX that is designed for flexibility.
Wiktionary dump file parser and multilingual data extractor
React-based framework with performance, scalability, and security built in.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.