Trending repositories: pytorch

19 of 19 repositories

• huggingface/transformers

  🤗 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.

  AI summary: The industry-standard library providing state-of-the-art Machine Learning models for PyTorch, TensorFlow, and JAX.

  166,951ai-mlPythonApache-2.0audiodeep-learningdeepseekgemma

• Comfy-Org/ComfyUI

  The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

  AI summary: A powerful, modular node-based GUI and backend engine for advanced diffusion model workflows.

  136,087ai-mlPythonGPL-3.0aicomfycomfyuipython

• rasbt/LLMs-from-scratch

  Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

  AI summary: Educational guide and code for building, training, and fine-tuning a Large Language Model from the ground up.

  106,008learningJupyter NotebookOtheraiartificial-intelligenceattention-mechanismdeep-learning

• jingyaogong/minimind

  🧠 Train a 64M-parameter LLM from scratch in just 2h!

  AI summary: A minimal, from-scratch PyTorch implementation of a large language model designed to train in hours on consumer GPUs.

  63,088ai-mlPythonApache-2.0artificial-intelligencelarge-language-modelpytorchllm

• ultralytics/ultralytics

  Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

  AI summary: The official framework for YOLOv8, offering state-of-the-art object detection and image segmentation.

  62,173ai-mlPythonAGPL-3.0computer-visiondeep-learningimage-classificationinstance-segmentation

• karpathy/nanochat

  The best ChatGPT that $100 can buy.

  AI summary: A minimalist, highly educational experimental harness for training and interacting with Large Language Models.

  58,389learningPythonMITeducationalllm-trainingmachine-learningpytorch

• roboflow/supervision

  We write your reusable computer vision tools. 💜

  AI summary: A reusable computer vision utility library for writing robust detection and tracking pipelines.

  51,108ai-mlPythonMITclassificationcococomputer-visiondeep-learning

• OpenBMB/VoxCPM

  VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

  AI summary: A 2B-parameter tokenizer-free speech model for 30-language synthesis, voice cloning, and zero-shot voice design.

  38,289ai-mlPythonApache-2.0audiodeeplearningminicpmmultilingual

• microsoft/onnxruntime

  ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

  AI summary: A cross-platform, high-performance machine learning inferencing and training accelerator.

  21,981ai-mlC++MITai-frameworkdeep-learninghardware-accelerationmachine-learning

• kyegomez/OpenMythos

  A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

  AI summary: A theoretical, open-source reconstruction of the Claude Mythos looped transformer architecture.

  14,905ai-mlPythonMITaianthropicattentionclaude

• FareedKhan-dev/train-llm-from-scratch

  A straightforward method for training your LLM, from downloading data to generating text.

  AI summary: A complete, from-scratch PyTorch tutorial for building and training large language models without opaque abstractions.

  11,942ai-mlPythonMITgeminilarge-language-modelsllmopenai

• Lightricks/LTX-2

  Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

  AI summary: An advanced open-source video generation model with sophisticated temporal, spatial, and audio synthesis capabilities.

  9,579ai-mlPythonOthergenerative-ailtxltx-2video-generation

• MakazhanAlpamys/Soup

  Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

  AI summary: A lightning-fast, C++ based LLM fine-tuning CLI that utilizes layer streaming.

  8,070ai-mlPythonApache-2.0cliconsumer-gpudpofine-tuning

• deepseek-ai/DeepSpec

  DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

  AI summary: A comprehensive toolkit for training and evaluating draft models used in speculative decoding.

  7,185ai-mlPythonMITspeculative-decodingdraft-modelsmodel-trainingllm-evaluation

• higgsfield-ai/higgsfield

  Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

  AI summary: A fault-tolerant GPU orchestration and training framework for scaling trillion-parameter models across multiple nodes.

  5,844infrastructureJupyter NotebookApache-2.0cluster-managementdeep-learningdistributedllama

• angelos-p/llm-from-scratch

  AI summary: An educational workshop guiding users through building a GPT model from scratch in PyTorch.

  3,420learningllmtransformermachine-learningeducational

• thu-pacman/chitu

  High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

  AI summary: A high-performance LLM inference framework optimized for efficiency and diverse hardware compatibility, including Chinese accelerators.

  2,987systemsPythonApache-2.0deepseekgpullmllm-serving

• Robbyant/lingbot-world-v2

  Infinite Worlds with Versatile Interactions

  AI summary: Advanced interactive world model enabling infinite horizons and highly diverse object interactions for robotic simulation.

  1,841ai-mlPythonOtherworld-modelrobotic-simulationvideo-generationembodied-ai

• livehl/aimirror

  🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来

  AI summary: A smart, parallel-download proxy that accelerates PyPI, Docker, CRAN, and HuggingFace in restricted corporate networks.

  215developer-toolsPythonMITai-toolscache-proxycudadeep-learning