Pretrained Models Python Packages

huggingface-hub

The official Python client for the Hugging Face Hub.

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.

timm

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-torch

An open source implementation of CLIP.

spaces

The official Python client for the Hugging Face Hub.

chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting

efficientnet-pytorch

A PyTorch implementation of EfficientNet

hf

The official Python client for the Hugging Face Hub.

silero

Silero Models: pre-trained text-to-speech models made embarrassingly simple

facenet-pytorch

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

efficientnet

Implementation of EfficientNet model. Keras and TensorFlow Keras.

pytorch-pretrained-bert

🤗 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.

clarifai

Experience the power of Clarifai’s AI platform with the python SDK. 🌟 Star to support our work!

pytorch-transformers-pvt-nightly

🤗 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.

geffnet

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

wtpsplit

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

paddlenlp

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

pytorch-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.

asteroid

The PyTorch-based audio source separation toolkit for researchers

spleeter

Deezer source separation library including pretrained models.

mmcls

OpenMMLab Pre-training Toolbox and Benchmark

open-image-models

Pre-trained image models using ONNX for fast, out-of-the-box inference.

image-classifiers

Classification models trained on ImageNet. Keras.

mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark