pretrained-models

The PyTorch-based audio source separation toolkit for researchers

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

GPT4V-level open-source multi-modal model based on Llama3-8B

An extension of Open3D to address 3D Machine Learning tasks

EasyNLP: A Comprehensive and Easy-to-use NLP Toolkit

Implementation of EfficientNet model. Keras and TensorFlow Keras.

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

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

This repo contains implementation of different architectures for emotion recognition in conversations.

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

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

💁 Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. 🛫☑️

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

中文法律LLaMA (LLaMA for Chinese legel domain)

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

A deep neural network that learns to drive in video games

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"

Fine-tune pretrained Convolutional Neural Networks with PyTorch

Shared Ultralytics logos, media, sample images, pretrained model weights, dataset artifacts, and release assets.

An implementation of the BERT model and its related downstream tasks based on the PyTorch framework. @跟我学机器学习

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

Discover pretrained models for deep learning in MATLAB

CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).

PyTorch Lightning Optical Flow models, scripts, and pretrained weights.

🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.