🤗 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.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
140,194 visible repositories in the index
1–24 of 61 · Most stars
🤗 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.
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
Deezer source separation library including pretrained models.
TranslatedThe official repo of Qwen chat & pretrained large language model proposed by Alibaba Cloud.
An open source implementation of CLIP.
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
A PyTorch implementation of EfficientNet
CodeGeeX2: A More Powerful Multilingual Code Generation Model
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
Translateda state-of-the-art-level open visual language model | multimodal pre-trained model
Chronos: Pretrained Models for Time Series Forecasting
A treasure chest for visual classification and recognition powered by PaddlePaddle
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
TranslatedAwesome Pretrained Chinese NLP Models, a collection of high-quality Chinese pretrained models, large models, multimodal models, and large language models
Superduper: End-to-end framework for building custom AI applications and agents.
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
Translated"Large Language Models" (《大语言模型》), authors: Zhao Xin, Li Junyi, Zhou Kun, Tang Tianyi, Wen Jirong
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488