verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

[NeurIPS 2024] Code release for "Segment Anything without Supervision"

Incredibly fast Whisper-large-v3

🔊 Text-Prompted Generative Audio Model

Stable-diffusion with Real-ESRGAN for upsampling

Autoregressive Entity Retrieval

AAAI ICWSM-2022 Evaluation of Fake News Detection with Knowledge-Enhanced Language Models

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.

PyTorch bottom-up attention with Detectron2

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

A Cog implementation of the Real-ESRGAN super-resolution model from ruDALL-E.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Mapping Wikipedia pages to Wikidata IDs and vice versa.

A tool for extracting plain text from Wikipedia dumps

🤗 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.