PyTorch
by Community
Tensors and Dynamic neural networks in Python with strong GPU acceleration
OSS
PyTorch
Added 1 June 2026
Overview
PyTorch is a Python library for building neural networks using tensors and dynamic computation graphs. It provides strong GPU acceleration through CUDA integration, allowing researchers and engineers to define and train models with flexible, define-by-run semantics.
Best for
Best for
ML researchers and engineers building custom neural network architectures with GPU training needs
Use cases
- Training deep learning models with GPU acceleration
- Research prototyping with dynamic neural network architectures
- Building production inference pipelines for computer vision and NLP
Notes
PyTorch is a Python library for building neural networks using tensors and dynamic computation graphs. It provides strong GPU acceleration through CUDA integration, allowing researchers and engineers to define and train models with flexible, define-by-run semantics.
100,318 stars on GitHub. Last updated 2026-06-01.
Use cases
- Training deep learning models with GPU acceleration
- Research prototyping with dynamic neural network architectures
- Building production inference pipelines for computer vision and NLP
Pros
- Dynamic computation graphs enable intuitive debugging and flexible model design
- Mature ecosystem with extensive pre-trained models and community libraries
- Strong GPU support with optimized kernels for training at scale
Cons
- Steeper learning curve than some alternatives for beginners
- Production deployment requires additional tooling beyond the core library
- Memory usage can be high for large models without careful optimization
Indexed from awesome-llmops and enriched against its public facts.
Pros
- Dynamic computation graphs enable intuitive debugging and flexible model design
- Mature ecosystem with extensive pre-trained models and community libraries
- Strong GPU support with optimized kernels for training at scale
Cons
- Steeper learning curve than some alternatives for beginners
- Production deployment requires additional tooling beyond the core library
- Memory usage can be high for large models without careful optimization
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
TensorFlow
Community
An Open Source Machine Learning Framework for Everyone
Jax
Community
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
PaddlePaddle
Community
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
Candle
Community
Minimalist ML framework for Rust
Apache MXNet
Community
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Caffe
Community
Caffe: a fast open framework for deep learning.
Candle
Community
Minimalist ML framework for Rust
Forward
Community
A library for high performance deep learning inference on NVIDIA GPUs.
Jax
Community
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
MegEngine
Community
MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架
MindSpore
Community
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
Oneflow
Community
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
PaddlePaddle
Community
PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）
TensorFlow
Community
An Open Source Machine Learning Framework for Everyone
TVM
Community
Open Machine Learning Compiler Framework
VectorFlow
Community
A minimalist neural network library optimized for sparse data and single machine environments.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
For-Sunny/hebbian-mind-enterprise
Various
Enterprise Hebbian neural graph for AI memory - CIPS LLC
goldmembrane/cleaner-code
Various
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated co
mindsdb/mindsdb
Various
Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and de
Alexander Rush Series
Community
Projects
Alpaca-LoRA-Serve
Community
LLM as a Chatbot Service
Archai
Community
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
Axolotl
Community
Go ahead and axolotl questions
Baichuan-7|13B
Community
AGI Large Language Models
bitsandbytes
Community
Accessible large language models via k-bit quantization for PyTorch.
BMTrain
Community
Efficient Training (including pre-training and fine-tuning) for Big Models
BudgetML
Community
Deploy a ML inference service on a budget in less than 10 lines of code.
Build a Large Language Model (From Scratch)
Community
How to implement LLM attention mechanisms and GPT-style transformers.
CodeT5
Community
Home of CodeT5: Open Code LLMs for Code Understanding and Generation
Comet
Community
Examples of Machine Learning code using Comet.ml
Deepchecks
Community
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
DeepSeek-V2.5
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
DeepSpeed
Community
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Determined
Community
Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch
disco-diffusion
Community
A frankensteinian amalgamation of notebooks, models and techniques for the generation of AI Art and Animations.
distilabel
Community
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
EasyEdit
Community
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
exllama
Community
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
FastEdit
Community
🩹Editing large language models within 10 seconds⚡
FedML
Community
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables runn
FLAML
Community
A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.
FlexGen
Community
Running large language models on a single GPU for throughput-oriented scenarios.
Flyflow
Community
Open source, high performance fine tuning as a service for GPT4 quality models with 5x lower latency and 3x lower cost
Forward
Community
A library for high performance deep learning inference on NVIDIA GPUs.
GLM-6B (ChatGLM)
Community
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Hands-On Large Language Models: Language Understanding and Generation
Community
Hands-On Large Language Models
Horovod
Community
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
hyperunity
Community
A toolset for black-box hyperparameter optimisation.
Infinity
Community
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Kubeflow
Community
Machine Learning Toolkit for Kubernetes
LangChain
Community
The agent engineering platform.
Liger-Kernel
Community
Efficient Triton Kernels for LLM Training
Litgpt
Community
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Lora
Community
Using Low-rank adaptation to quickly fine-tune diffusion models.
Ludwig
Community
Low-code framework for building custom LLMs, neural networks, and other AI models
M3CoT
Community
Leaderboard | M 3 CoT
Megatron-LM
Community
Ongoing research training transformer models at scale
Model Search
Community
NASGym
Community
A simple OpenAI Gym environment for Neural Architecture Search (NAS)
NeMo Framework
Community
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech
NNI
Community
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
OneComp
Community
Python package for LLM compression
open-r1
Community
Fully open reproduction of DeepSeek-R1
OpenVLA
Community
OpenVLA: An open-source vision-language-action model for robotic manipulation.
peft
Community
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Qwen-VL-7B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Qwen2-Math-1.5B|7B|72B
Community
GITHUB HUGGING FACE MODELSCOPE DISCORD 🚨 This model mainly supports English. We will release bilingual (English and Chinese) math models soon. Introduction Over the past year, w
RoboMamba
Community
An efficient VLA model leveraging State Space Models (Mamba) instead of standard self-attention, offering linear inference complexity for efficient, recurrent robotic reasoning.
ROLL
Community
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
segment-anything (SAM)
Community
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
SGLang
Community
SGLang is a high-performance serving framework for large language models and multimodal models.
SmolVLA
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StableLM-3B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StarCoder-1|3|7B
Community
All models, datasets, and demos related to StarCoder!
TGI
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
TinyZero
Community
Minimal reproduction of DeepSeek R1-Zero
Torchserve
Community
Serve, optimize and scale PyTorch models in production
Transformer Engine
Community
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide b
Transformers Agents
Community
Provides a natural language API on top of transformers
Triton Server (TRTIS)
Community
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
TVM
Community
Open Machine Learning Compiler Framework
veRL
Community
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Vision agent
Community
This tool has been deprecated. Use Agentic Document Extraction instead.
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
xTuring
Community
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: htt
Yi-34B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Zetane Viewer
Community
ML models and internal tensors 3D visualizer
Build a Reasoning Model (From Scratch)
Various
Understand LLM reasoning by creating your own reasoning model–from scratch! LLM reasoning models have the power to tackle truly challenging problems that require finding the righ
Forefront
Various
Forefront is a platform to fine-tune and inference open-source-language-models.
Hugging Face Diffusion Models Course
Various
Materials for the Hugging Face Diffusion Models Course
Make-A-Scene
Various
Make-A-Scene by Meta is a multimodal generative AI method puts creative control in the hands of people who use it by allowing them to describe and illustrate their vision through b
MetaGPT
Various
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Together AI
Various
Build what's next on the AI Native Cloud. Full-stack AI platform for inference, fine-tuning, and GPU clusters — powered by cutting-edge research.
TTS WebUI
Various
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, S
Unsloth
Various
Unsloth is an open-source, no-code web UI for training, running and exporting open models in one unified local interface.
AgentForge
Community
Extensible AGI Framework
Automata
Community
Automata: A self-coding agent
BambooAI
Community
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
gpt-migrate
Community
Easily migrate your codebase from one language or framework to another.
UFO
Community
UFO³: Weaving the Digital Agent Galaxy
vortic
Community
Co-founder's LinkedIn 1
Acacian/aegis
Various
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One
AgiMaulana/HuaweiAppGalleryMcp
Various
AgiMaulana/HuaweiAppGalleryMcp — indexed from awesome-mcp-servers-punkpeye
AlexanderLawson17/revettr-python
Various
Python client SDK for Revettr counterparty risk scoring API
bx33661/Wireshark-MCP
Various
Wireshark-MCP，Give your AI assistant a packet analyzer. Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
crystaldba/postgres-mcp
Various
Postgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.
cyntrisec/cyntrisec-cli
Various
Historical AWS analysis CLI; not a current Cyntrisec product
DataEval/dingo
Various
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
For-Sunny/hebbian-mind-enterprise
Various
Enterprise Hebbian neural graph for AI memory - CIPS LLC
haoyifan/Silicon-Pantheon
Various
Silicon Pantheon - Tactics game played by AI agents coached by human
hydrolix/mcp-hydrolix
Various
An MCP server for Hydrolix
Infrawise/mcp-server
Various
Infrawise MCP server for Claude Code — Azure FinOps cost optimization
johnanleitner1-Coder/lastminutedeals-api
Various
FOR SALE $8K — Production AI travel booking engine. 47 live suppliers, 18 countries, MCP server (Smithery + Glama), Stripe payments, OCTO/Bokun API. See /for-sale page.
microsoft/markitdown
Various
Python tool for converting files and office documents to Markdown.
mikan-atomoki/text-to-model
Various
mikan-atomoki/text-to-model — indexed from awesome-mcp-servers-punkpeye
nonameuserd/paybond-kit
Various
TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and s
nyxn-ai/NyxDocs
Various
Cryptocurrency Documentation MCP Server - AI-powered documentation collection and management system for blockchain projects
pythonanywhere/pythonanywhere-mcp-server
Various
🐍 🏠 - MCP server implementation for PythonAnywhere cloud platform.
rafsilva85/credit-optimizer-v5
Various
Save 47% on Manus AI credits automatically. Zero downsides. Pays for itself in ~27 prompts. Free MCP Server (PyPI) + $12 Manus Skill bundle with Fast Navigation (115x speed boost).
Ratnaditya-J/csvglow
Various
Generate beautiful interactive HTML dashboards from CSV/Excel files
rejifald/StitchAPI
Various
The agent-native runtime where a typed, declarative stitch replaces fetch — for humans and agents alike.
rocketride-org/rocketride-server
Various
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent
rossshannon/Weekly-Weather-mcp
Various
Weather MCP server which returns 7 days of detailed weather forecasts anywhere in the world
ShinyDapps/l402-kit
Various
The simplest way to charge for your API in Bitcoin sats. 3 lines of code. TypeScript + Python. Lightning Network L402 protocol.
srinath1510/alltrails-mcp-server
Various
DEPRECATED: MCP server that provides access to AllTrails data, allowing you to search for hiking trails and get detailed trail information directly through Claude Desktop.
video-edit-mcp
Various
🐍 🏠 🍎 🪟 - Comprehensive video and audio editing MCP server with advanced operations including trimming, merging, effects, overlays, format conversion, audio processing, YouTube
Zhonghao1995/agentic-swmm-workflow
Various
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Ski
Accelerate
Community
🚀 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 a
Agentic Radar
Community
A security scanner for your LLM agentic workflows
AgentScope
Community
Build and run agents you can see, understand and trust.
Alpaca-LoRA-Serve
Community
LLM as a Chatbot Service
AudioGPT
Community
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Auto-PyTorch
Community
Automatic architecture search and hyperparameter optimization for PyTorch
AutoGL
Community
An autoML framework & toolkit for machine learning on graphs.
Axolotl
Community
Go ahead and axolotl questions
Baichuan-7|13B
Community
AGI Large Language Models
bark
Community
🔊 Text-Prompted Generative Audio Model
BELLE
Community
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Build a Large Language Model (From Scratch)
Community
How to implement LLM attention mechanisms and GPT-style transformers.
ChatGLM2-6B
Community
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Clip-as-a-service
Community
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
CodeGeeX
Community
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
CodeQwen1.5-7B
Community
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction The advent of advanced programming tools, which harnesses the power of large language models (LLMs), has significantly en
Codestral-7|22B
Community
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
CodeT5
Community
Home of CodeT5: Open Code LLMs for Code Understanding and Generation
Colossal-AI
Community
Making large AI models cheaper, faster and more accessible
Datatrove
Community
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Deepchecks
Community
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
DeepSeek-R1
Community
First-generation reasoning models from DeepSeek.
DeepSeek-Math-7B
Community
DeepSeek Math series
DeepSeek-V2.5
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
DeepSeek-VL-1.3|7B
Community
DeepSeek-VL model series
Determined
Community
Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch
Dragonfly
Community
An open source python library for scalable Bayesian optimisation.
EasyFL
Community
An easy-to-use federated learning platform
Falcon 40B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
FastChat
Community
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
fauxpilot
Community
FauxPilot - an open-source alternative to GitHub Copilot server
FedML
Community
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables runn
Fiddler AI
Community
Fiddler Auditor is a tool to evaluate language models.
finetuning-scheduler
Community
A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
FlagAI
Community
FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.
FlexGen
Community
Running large language models on a single GPU for throughput-oriented scenarios.
Flower
Community
Flower: A Friendly Federated AI Framework
Flyflow
Community
Open source, high performance fine tuning as a service for GPT4 quality models with 5x lower latency and 3x lower cost
GLM-2|6|10|13|70B
Community
Org profile for THUDM on Hugging Face, the AI community building the future.
GLM-6B (ChatGLM)
Community
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Gorilla
Community
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
GPT-NeoX
Community
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
hyperunity
Community
A toolset for black-box hyperparameter optimisation.
IBM data-prep-kit
Community
Open source project for data preparation for GenAI applications
Improving language models by retrieving from trillions of tokens
Community
Publications — Google DeepMind
Infinity
Community
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
InternLM-XComposer2-1.8|7B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
InternLM2-1.8|7|20B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
LawBench
Community
LawBench
LazyLLM
Community
Easiest and laziest way for building multi-agent LLMs applications.
learn2learn
Community
A PyTorch Library for Meta-learning Research
LeRobot
Community
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Llama 3.2-1|3|11|90B
Community
[Llama 3.1-8 70 405B](https://llama.meta.com/)
Llama 3-8|70B
Community
[Llama 2-7 13 70B](https://llama.meta.com/llama2/)
LLM Agents
Community
Build agents which are controlled by LLMs
Llmware
Community
Unified framework for building enterprise RAG pipelines with small, specialized models
LMDeploy
Community
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Lora
Community
Using Low-rank adaptation to quickly fine-tune diffusion models.
Ludwig
Community
Low-code framework for building custom LLMs, neural networks, and other AI models
Maniford
Community
A model-agnostic visual debugging tool for machine learning
Marvin
Community
an ambient intelligence library
MathEval
Community
a comprehensive benchmarking platform designed to evaluate large models' mathematical abilities across 20 fields and nearly 30,000 math problems.
Megatron-DeepSpeed
Community
Ongoing research training transformer language models at scale, including: BERT & GPT-2
Megatron-LM
Community
Ongoing research training transformer models at scale
Meta Lingua
Community
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
midjourney
Community
Midjourney is an independent research lab exploring new mediums of thought and expanding the imaginative powers of the human species.
MiniCPM-2B
Community
The MiniCPM family of LLMs and VLLMs.
MMedBench
Community
Medical Multilingual Benchmark
MM ReAct
Community
Official repo for MM-REACT
MMToM-QA
Community
Leaderboard for the MMToM-QA benchmark (Jin et al., ACL 2024).
Mosec
Community
A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine
nanotron
Community
Minimalistic large language model 3D-parallelism training
NeMo Framework
Community
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech
Octo
Community
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
octoml-profile
Community
Home for OctoML PyTorch Profiler
OLMo-7B
Community
Artifacts for the first set of OLMo models.
OLMO-eval
Community
Evaluation suite for LLMs
Omnigraph
Community
Lakehouse native graph engine with git-style workflows
OneComp
Community
Python package for LLM compression
OneKE
Community
About OneKEOneKE is a new v...
open-r1
Community
Fully open reproduction of DeepSeek-R1
OpenELM-1.1|3B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
OpenPI
Community
Open-source VLA models from Physical Intelligence, including π₀ and π₀.5 — flow-based vision-language-action models pretrained on large-scale robot data with fine-tuning support.
OpenVLA
Community
OpenVLA: An open-source vision-language-action model for robotic manipulation.
p-tuning-v2
Community
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
PaLM-E: An Embodied Multimodal Language Model
Community
Project page for PaLM-E: An Embodied Multimodal Language Model.
peft
Community
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Phi1-1.3B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Pythia-1|1.4|2.8|6.9|12B
Community
The hub for EleutherAI's work on interpretability and learning dynamics
PyTorch Lightning
Community
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Qwen-1.8B|7B|14B|72B
Community
Qwen - a Qwen Collection
Qwen-VL-7B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Qwen2-0.5B|1.5B|7B|57B-A14B-MoE|72B
Community
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD Introduction After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: Pret
Qwen2.5-1M-7|14B
Community
Tech Report HuggingFace ModelScope Qwen Chat HuggingFace Demo ModelScope Demo DISCORD Introduction Two months after upgrading Qwen2.5-Turbo to support context length up to one mi
Qwen2.5-Max
Community
QWEN CHAT API DEMO DISCORD It is widely recognized that continuously scaling both data size and model size can lead to significant improvements in model intelligence. However, th
Qwen2-Audio-7B
Community
DEMO PAPER GITHUB HUGGING FACE MODELSCOPE DISCORD To achieve the objective of building an AGI system, the model should be capable of understanding information from different moda
Rhesis
Community
The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root ca
RoboMamba
Community
An efficient VLA model leveraging State Space Models (Mamba) instead of standard self-attention, offering linear inference complexity for efficient, recurrent robotic reasoning.
RWKV-v4|5|6
Community
Org profile for RWKV on Hugging Face, the AI community building the future.
segment-anything (SAM)
Community
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
SGLang
Community
SGLang is a high-performance serving framework for large language models and multimodal models.
Shimmy
Community
⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.
simulate-sdk
Community
Enterprise Grade, Voice AI simulation SDK for testing your AI Agents
SmolVLA
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StableLM-v2-12B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
StableLM-3B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
stable-diffusion
Community
A latent text-to-image diffusion model
TAT-DQA
Community
TAT-DQA: A Document Visual Question Answering (VQA) Dataset, aiming to answer questions over visually-rich documents with a hybrid of Tabular and Textual Content in Finance
text-generation-inference
Community
Large Language Model Text Generation Inference
ThinkGPT
Community
Agent techniques to augment your LLM and push it beyong its limits
tokenizers
Community
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
TinyZero
Community
Minimal reproduction of DeepSeek R1-Zero
Torchmeta
Community
A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch
torchtitan
Community
A PyTorch native platform for training generative AI models
torchtune
Community
PyTorch native post-training library
TRL
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Tune Studio
Community
Playground for devs to finetune & deploy LLMs
TVM
Community
Open Machine Learning Compiler Framework
unslothai
Community
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
UQLM
Community
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
Vegas
Community
AutoML tools chain
veRL
Community
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
VisCPM-10B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
VisualWebArena
Community
Project webpage for the VisualWebArena paper.
WebGPT: Browser-assisted question-answering with human feedback
Community
2021-12
whisper
Community
Robust Speech Recognition via Large-Scale Weak Supervision
x-stable-diffusion
Community
Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6
Yi-34B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Yi-VL-6B|34B
Community
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
AIVA
Various
AIVA, your AI music generation assistant
Artbreeder
Various
A collaborative tool for creating images with AI.
Autodesk Flow Studio
Various
Explore powerful features like AI-driven mocap, camera tracking, animation, and compositing tools in Autodesk Flow Studio.
Bloom
Various
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Build a DeepSeek Model (From Scratch)
Various
Learn how to build the features that set DeepSeek apart from other top LLMs! When DeepSeek started making waves in January 2025, it sounded too good to be true. How could a gener
ComfyUI
Various
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
D-ID
Various
D-ID | The #1 Choice for AI Generated Video Creation Platform
DeepSeek
Various
Org profile for DeepSeek on Hugging Face, the AI community building the future.
DragGAN
Various
Official Code for DragGAN (SIGGRAPH 2023)
Flux
Various
Official inference repo for FLUX.1 models
GitHub Copilot
Various
Today, we're launching a technical preview of GitHub Copilot, a new AI pair programmer that helps you write better code.
GLM
Various
GLM-5: From Vibe Coding to Agentic Engineering
Harmonai
Various
Harmonai.org
Hex
Hex Technologies
Collaborative analytics with AI. SQL, Python, and an agent that helps you explore data and ship dashboards.
Jenni
Various
Jenni is an AI research and academic writing assistant that helps students, researchers, and academics create essays, papers, and citations with ease.
LLaMA
Various
Llama LLM, a foundational, 65-billion-parameter large language model by Meta. Meta, February 23rd, 2023. #opensource
Ludwig
Various
Low-code framework for building custom LLMs, neural networks, and other AI models
Make-A-Scene
Various
Make-A-Scene by Meta is a multimodal generative AI method puts creative control in the hands of people who use it by allowing them to describe and illustrate their vision through b
Meta AI
Various
Meta AI assistant to get things done, create AI-generated images, get answers. Built on Llama LLM.
Midjourney
Various
Midjourney is an independent research lab exploring new mediums of thought and expanding the imaginative powers of the human species.
MetaGPT
Various
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Mistral
Various
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
OPT
Various
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
QuillBot
Various
Write effortlessly and efficiently with Quillbot's suite of AI tools. Paraphrase, check grammar, analyze tone, improve fluency, and more. Start doing your best work.
Resemble AI
Various
Resemble AI helps enterprises generate secure voice AI, verify proper usage, and detect deepfakes instantly. Available on-prem or via cloud. Built for enterprise scale with gover
RunThisLLM
Various
Find out exactly what hardware you need to run any local LLM, image, video, or audio AI model. 275+ models with full build specs and performance estimates.
Runway
Various
We are building foundational General World Models that will be capable of simulating all possible worlds and experiences. The next frontier of intelligence will come from models
Sora
Various
Presentation of Sora, a large video generation model. OpenAI, February 15, 2024.
Stable Audio
Various
Learn about Stable Audio 3.0, a model family trained on fully licensed data, designed to be the foundation for what the audio community builds next. Three of the models are open
Stable Diffusion Public Release
Various
We are delighted to announce the public release of Stable Diffusion and the launch of DreamStudio Lite.
Stable Diffusion
Various
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
STORM
Various
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. [#opensource](https://github.com/stanford-oval/storm/)
Suno AI
Various
Create stunning original music for free in seconds using our AI generator. Make your own masterpieces, share with friends, and discover music from artists worldwide.
SymbolicAI
Various
A neurosymbolic perspective on LLMs
TorToiSe
Various
A multi-voice TTS system trained with an emphasis on quality
Vicuna-13B
Various
We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation using GPT-4 as a judge s
Whisper
Various
Robust speech recognition via large-scale weak supervision. [#opensource](https://github.com/openai/whisper)
Aim
Community
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Awesome Production Machine Learning
Community
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
ClearML
Community
ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution
conda
Community
A system-level, binary package and environment manager running on all major operating systems and platforms.
DVC
Community
🦉 Data Versioning and ML Experiments
envd
Community
🏕️ Reproducible development environment for humans and agents
FasterTransformer
Community
Transformer related optimization, including BERT, GPT
Feast
Community
The Open Source Feature Store for AI/ML
FedML
Community
FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables runn
Forward
Community
A library for high performance deep learning inference on NVIDIA GPUs.
Goptuna
Community
A hyperparameter optimization framework, inspired by Optuna.
Guild AI
Community
Experiment tracking, ML developer tools
Harmonia
Community
Federated Learning Made Easy
HpBandSter
Community
a distributed Hyperband implementation on Steroids
Hyperband
Community
Tuning hyperparams fast with Hyperband
HPOlib2
Community
Collection of hyperparameter optimization benchmark problems
Hyperopt
Community
Distributed Asynchronous Hyperparameter Optimization in Python
hyperunity
Community
A toolset for black-box hyperparameter optimisation.
Jupyter Notebooks
Community
Jupyter Interactive Notebook
Katib
Community
Automated Machine Learning on Kubernetes
Kedro-Viz
Community
Visualise your Kedro data and machine-learning pipelines and track your experiments.
LabNotebook
Community
LabNotebook is a tool that allows you to flexibly monitor, record, save, and query all your machine learning experiments.
Metaflow
Community
Build, Manage and Deploy AI/ML Systems
metric-learn
Community
Metric learning algorithms in Python
ModelFox
Community
ModelFox makes it easy to train, deploy, and monitor machine learning models.
MOE
Community
A global, black box optimization engine for real world metric optimization.
NCNN
Community
ncnn is a high-performance neural network inference framework optimized for the mobile platform
netron
Community
Visualizer for neural network, deep learning and machine learning models
ONNX-MLIR
Community
Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure
optimum-tpu
Community
Google TPU optimizations for transformers models
ormb
Community
Docker for Your ML/DL Models Based on OCI Artifacts
PAI
Community
Resource scheduling and cluster management for AI
Sacred
Community
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
scalene
Community
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
scikit-learn
Community
scikit-learn: machine learning in Python
Spearmint
Community
Spearmint Bayesian optimization codebase
TensorBoard
Community
TensorFlow's Visualization Toolkit
TVM
Community
Open Machine Learning Compiler Framework
Volcano
Community
A Cloud Native Batch System (Project under CNCF)
Weco Observe
Community
Build and Optimize your machine learning pipeline with the Weco Platform - based on AIDE ML, the LLM-powered code optimization Agent for Machine Learning Engineering.
Weights & Biases
Community
W&B Weave helps developers evaluate, monitor, and iterate continuously to deliver generative AI applications with confidence.
whylogs
Community
An open-source data logging library for machine learning models and data pipelines. 📚 Provides visibility into data quality & model performance over time. 🛡️ Supports privacy-pre
XGBoost
Community
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and D
ZenML
Community
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.