tracel-ai/models

Models and examples built with Burn

What it solves

This repository provides a centralized collection of deep learning model implementations and examples built using the Burn deep learning framework. It allows developers to easily find and integrate various pre-existing model architectures across different modalities.

How it works

The project acts as a hub for both official implementations and community-contributed models. It organizes models by their function, such as language modeling, image classification, and speech recognition, providing links to the specific repositories where the code is hosted.

Who it’s for

Developers and researchers using the Burn framework who need ready-made model architectures to implement in their projects.

Highlights

  • Diverse Modalities: Includes models for text (ALBERT, RoBERTa, Llama 2, RWKV v7), images (ResNet, MobileNetV2, YOLOX, Stable Diffusion), and audio/speech (Whisper, Wav2Vec 2.0, OmniVoice).
  • Official and Community Support: Combines a set of official Burn models with a curated list of community-developed implementations.
  • Broad Application Range: Covers everything from object detection and OCR to voice cloning and music note detection.

Related

  • Project
    microsoft/unilm

    A comprehensive collection of foundation models and architectures from Microsoft focusing on large-scale self-supervised pre-training across text, vision, speech, and multimodal tasks.

  • Project
    apple/corenet

    A deep neural network toolkit for training standard and novel AI models, ranging from small-scale tasks to large-scale foundation models like LLMs and CLIP.

  • Project
    jolibrain/deepdetect

    A deep learning runtime and REST server that provides a unified CLI and API for training and serving models across multiple data modalities.

  • Project
    huggingface/transformers

    A model-definition framework for state-of-the-art machine learning that provides a unified API for inference and training across text, vision, audio, and multimodal models.

  • Project
    tracel-ai/burn

    A deep learning framework and tensor library in Rust that unifies training and inference into a single codebase for seamless deployment across diverse hardware.