🤗 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.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

An extremely fast Python package and project manager, written in Rust.

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

Safety checks Python dependencies for known security vulnerabilities and suggests the proper remediations for vulnerabilities detected.

Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more

Simple package to extract text with coordinates from programmatic PDFs

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

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

A collection of useful .gitignore templates

Simplify your onnx model

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

This repository contains demos I made with the Transformers library by HuggingFace.

Website and blog generator for Go, Node.js or Python

Community-driven collection of Jetpack Compose example code and tutorials 🚀 https://foso.github.io/compose

Starter template for use with the Leptos web framework.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Best (most accurate) trained LSTM models.

A Docker image for PyTorch

Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

Docker-Compose template for orchestrating a Flask app with a Celery queue using Redis

Implementation of DocFormer: End-to-End Transformer for Document Understanding, a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU)

A Hacker News lookalike written in Python/Django, powering https://news.python.sc

NVIDIA's Deep Imagination Team's PyTorch Library

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

A small Django application to advertise the fun htmx can bring you

Text and Layout Document Image Understanding. LayoutLM