Hot Reloading and Profiling for Python

Conditionally run actions based on files modified by PR, feature branch or pushed commits

A conda-forge distribution.

💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline

python decorators made easy.

Detect file content types with deep learning

A library that integrates huggingface transformers with the world of fastai, giving fastai devs everything they need to train, evaluate, and deploy transformer specific models.

Distribute and run LLMs with a single file.

Run your GitHub Actions locally 🚀

Code repository for our paper presenting the L3D dataset.

Ultralytics YOLO11 🚀

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A tiny library for coding with large language models.

A SQLite extension for efficient vector search, based on Faiss!

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

A Repo For Document AI

A Unified Toolkit for Deep Learning Based Document Image Analysis

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

📋 A list of open LLMs available for commercial use.

Represent, send, store and search multimodal data

Official Code for DragGAN (SIGGRAPH 2023)

Interact with your documents using the power of GPT, 100% privately, no data leaks

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

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Scriopt that checks for MOT cancellations