Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

Scripts, configs and documentation for the pre- and midtraining activities of the Soofi Project.

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…

Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs

Native macOS semantic search over your local files - text, images, audio, video in one vector space, on-device on Apple silicon.

Git-backed, Overleaf-style autosave for LaTeX — right inside VS Code.

RecTools - library to build Recommendation Systems easier and faster than ever before

GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.

Official repo of Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models

Ad Tech for ML/RL Practitioners: A hands-on introduction to advertising technology

LREC2026 Tutorial "Low-Resource, High-Impact: Building Corpora for Inclusive Language Technologies"

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

CHURRO is an OCR toolkit for historical document transcription, built to make handwritten and printed sources readable at high accuracy and lower cost.

Tools to build fast quality classifiers for Olmo data filtering

Multi-Agent Harness for Production AI

A Grapheme to Phoneme model using LSTM implemented in pytorch

A tool for translating Persian text to IPA (International Phonetic Alphabet).

Universal Romanizer that can convert any unicode script to roman (latin) script

AI that sees your screen, listens to your conversations and tells you what to do

Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.

Normalize any language identifier to canonical ISO 639-3 + ISO 15924 form. Powered by LinguaMeta from Google Research

Language metadata toolkit (QwanQwa)

AI agents running research on Hugging Face infra

OCR model that handles complex tables, forms, handwriting with full layout.

AI agents running research on single-GPU nanochat training automatically

OpenLID-v3