pytorch
45 个已发布仓库。
| 仓库 | |||||
|---|---|---|---|---|---|
| 1 |
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.
|
169k | +0.0% | +0.2% | 58 |
| 2 |
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.
|
146.9k | +0.1% | +0.9% | 105 |
| 3 |
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
|
108.4k | +0.0% | +0.4% | 90 |
| 4 |
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
|
97k | +0.0% | +0.4% | 71 |
| 5 |
labmlai/annotated_deep_learning_paper_implementations
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
|
67.8k | -0.0% | +0.0% | 30 |
| 6 |
keras-team/keras
Deep Learning for humans
|
64.4k | -0.0% | +0.0% | 15 |
| 7 |
ultralytics/ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
|
63.4k | +0.1% | +0.4% | 42 |
| 8 |
ultralytics/yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
|
58.3k | +0.0% | +0.0% | 25 |
| 9 |
roboflow/supervision
We write your reusable computer vision tools. 💜
|
51.6k | +0.0% | +0.2% | 36 |
| 10 |
ray-project/ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
|
44.3k | +0.0% | +0.1% | 12 |
| 11 |
deepspeedai/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
|
43.3k | -0.0% | +0.0% | 17 |
| 12 |
OpenBMB/VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
|
42.5k | +0.1% | +2.2% | 100 |
| 13 |
huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
|
37.3k | +0.0% | +0.0% | 13 |
| 14 |
NandhaKishorM/laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
|
35.5k | +0.1% | +1.0% | 613 |
| 15 |
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
|
34.9k | -0.0% | +0.1% | 21 |
| 16 |
lutzroeder/netron
Visualizer for neural network, deep learning and machine learning models
|
33.7k | +0.0% | +0.1% | 6 |
| 17 |
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
|
31.4k | -0.0% | +0.0% | 11 |
| 18 |
deepinsight/insightface
State-of-the-art 2D and 3D Face Analysis Project
|
30.2k | +0.0% | +0.2% | 9 |
| 19 |
JaidedAI/EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
|
30.1k | +0.0% | +0.0% | 12 |
| 20 |
fastai/fastai
The fastai deep learning library
|
28.3k | +0.0% | +0.0% | 8 |
| 21 |
Anjok07/ultimatevocalremovergui
GUI for a Vocal Remover that uses Deep Neural Networks.
|
27.2k | +0.1% | +0.6% | 12 |
| 22 |
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
|
24.1k | -0.0% | +0.0% | 7 |
| 23 |
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
|
24.1k | +0.0% | +0.1% | 7 |
| 24 |
lukasmasuch/best-of-ml-python
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
|
23.9k | -0.0% | +0.0% | 11 |
| 25 |
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
|
22.3k | +0.0% | +0.2% | 8 |
| 26 |
huggingface/datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
|
22.1k | +0.0% | +0.1% | 9 |
| 27 |
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
|
21.9k | +0.0% | +0.1% | 15 |
| 28 |
onnx/onnx
Open standard for machine learning interoperability
|
21.7k | +0.0% | +0.1% | 6 |
| 29 |
AI4Finance-Foundation/FinGPT
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
|
21.6k | +0.0% | +0.2% | 16 |
| 30 |
modelscope/FunASR
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
|
21k | +0.0% | +0.3% | 14 |
| 31 |
stas00/ml-engineering
Machine Learning Engineering Open Book
|
19.7k | +0.0% | +0.2% | 9 |
| 32 |
mrdbourke/pytorch-deep-learning
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
|
19.4k | +0.0% | +0.1% | 10 |
| 33 |
arc53/DocsGPT
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
|
18.4k | +0.0% | +0.1% | 13 |
| 34 |
bharathgs/Awesome-pytorch-list
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
|
16.8k | +0.0% | +0.1% | 5 |
| 35 |
tracel-ai/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
|
16.3k | +0.0% | +0.1% | 10 |
| 36 |
kubeflow/kubeflow
The Cloud Native AI Platform
|
16k | +0.0% | +0.1% | 5 |
| 37 |
NVIDIA/TensorRT-LLM
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
|
15.1k | +0.0% | +0.3% | 13 |
| 38 |
DataTalksClub/machine-learning-zoomcamp
Learn ML engineering for free in 4 months! Register here 👇🏼
|
15k | +0.0% | +0.2% | 6 |
| 39 |
kyegomez/OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
|
14.9k | +0.0% | +0.0% | 71 |
| 40 |
BlinkDL/RWKV-LM
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
|
14.8k | -0.0% | +0.0% | 8 |
| 41 |
flairNLP/flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
|
14.4k | +0.0% | +0.0% | 5 |
| 42 |
mlfoundations/open_clip
An open source implementation of CLIP.
|
14.3k | +0.0% | +0.1% | 7 |
| 43 |
isl-org/Open3D
Open3D: A Modern Library for 3D Data Processing
|
14.2k | +0.0% | +0.2% | 4 |
| 44 |
unifyai/ivy
Convert Machine Learning Code Between Frameworks
|
14.2k | +0.0% | -0.0% | 7 |
| 45 |
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
|
14k | +0.0% | +0.2% | 6 |