Stars
Code to obtain the CNN / Daily Mail dataset (non-anonymized) for summarization
Train the smallest LM you can that fits in 16MB. Best model wins!
A small GUI library for Wayland client programming - rendered with Skia
AI-powered penetration testing using autonomous agents — directly in your terminal.
Listado de comunidades, provincias, municipios con su correspondiente código INE
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
A collection of raw text from various Greek dialects
SacreROUGE is a library dedicated to the use and development of text generation evaluation metrics with an emphasis on summarization.
Find, verify, and analyze leaked credentials
Romanian Named Entity Corpus (RONEC) version 2.0
Give your agents the power of the Hugging Face ecosystem
The open-source voice synthesis studio
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
Useful datasets, specific to Georgia
Distillation of KoBERT from SKTBrain (Lightweight KoBERT)
Portuguese pre-trained BERT models
A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.
Distributed, offline-first bug tracker embedded in git
PaperBanana: Automating Academic Illustration For AI Scientists
This API provides programmatic access to the AlphaGenome model developed by Google DeepMind.