DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. All in a modern, AI-native editor.

Run PyTorch LLMs locally on servers, desktop and mobile

Find dead Python code

Grok open release

Automatically commit and push changed files back to GitHub with this GitHub Action for the 80% use case.

Generative Models by Stability AI

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

All things prompt engineering

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Scalable and flexible workflow orchestration platform that seamlessly unifies data, ML and analytics stacks.

The API traffic analyzer for Kubernetes providing real-time K8s protocol-level visibility, capturing and monitoring all traffic and payloads going in, out and across containers, pods, nodes and clu…

David Attenborough narrates your life

A webhook for Buildkite to notify users via DM on Slack for failed builds.

a state-of-the-art-level open visual language model | 多模态预训练模型

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

A Pythonic framework to simplify AI service building

PyTorch code and models for the DINOv2 self-supervised learning method.

LLM inference in C/C++

Foundational Models for State-of-the-Art Speech and Text Translation

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing d…

This repository contains tutorials and examples for Triton Inference Server

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

Run your GitHub Actions locally 🚀

Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and mo…

An open source implementation of CLIP.