YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

A high-throughput and memory-efficient inference and serving engine for LLMs

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Structured Text Generation

Large Language Model Text Generation Inference

structured outputs for llms

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

A framework for few-shot evaluation of language models.

Accessible large language models via k-bit quantization for PyTorch.

A Python wrapper for Google Tesseract

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Large-scale LLM inference engine

Benchmarking PDF libraries

Source code for the paper "Lightweight Photometric Stereo for Facial Details Recovery" (CVPR2020).

Estimates a depth mapping from a given normal mapping.

This repository contains an implementation of the LLaMA 2 (Large Language Model Meta AI) model, a Generative Pretrained Transformer (GPT) variant. The implementation focuses on the model architectu…

Total Deep Variation Regularizer

Get 3-D picture by using lighting image from three sides

Normal Integration by solving a discrete object.