🤗 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.

Train transformer language models with reinforcement learning.

QCAD - The Open Source 2D CAD. QCAD is a cross-platform CAD solution for Windows, macOS and Linux. It supports the DXF format and optionally the DWG format (through a proprietary plugin).

A general fine-tuning kit geared toward image/video/audio diffusion models.

Free and Open source Web Builder Framework. Next generation tool for building templates without coding

The public CGAL repository, see the README below

A collection of apps built on Electron

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

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

GRUEN for Evaluating Linguistic Quality of Generated Text (EMNLP 2020 Findings)

This repository is deprecated and no longer maintained.

Official repository for our work on micro-budget training of large-scale diffusion models.

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

some training polygons algorithms

Reference implementation for DPO (Direct Preference Optimization)

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)

Simple image captioning model

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

SVG path low level transformations toolkit

Provides ROS integration for Cartographer.

GLIDE: a diffusion-based text-conditional image synthesis model

High-Resolution Image Synthesis with Latent Diffusion Models

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

An open source vector nesting tool

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Cartographer is a system that provides real-time simultaneous localization and mapping (SLAM) in 2D and 3D across multiple platforms and sensor configurations.

Simple raster image tracer and vectorizer written in JavaScript.

An implementation of the Graham's Scan Convex Hull algorithm in JavaScript.