pretrained-models

transformers

+293

🤗 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.

pyannote-audio

+42

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

pytorch-image-models

+23

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

open_clip

+20

An open source implementation of CLIP.

huggingface_hub

+18

The official CLI and Python client for the Hugging Face Hub.

chronos-forecasting

+28

Chronos: Pretrained Models for Time Series Forecasting

jeffy

+9

Pretrained text classifiers you can run and retrain on CPU

lightly-train

+9

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

LimiX

+9

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488