Showing 1-20 of 117 projects
Model framework for state-of-the-art ML models in text, vision, audio, and multimodal tasks.
Comprehensive Chinese NLP resource collection for developers
Converts complex documents into LLM-ready formats for agentic workflows
A collection of PyTorch image encoders/backbones with training, evaluation, and inference scripts.
Industrial-strength NLP library for Python with pretrained models and fast processing
CLIP is a neural network for zero-shot image-text matching and understanding
PyTorch Lightning simplifies deep learning training and deployment at scale.
Source separation library for audio processing with pretrained models
Minimal PyTorch GPT re-implementation for training and inference
Qwen is a large language model series by Alibaba Cloud with multiple variants and capabilities.
Janus-Series: Unified Multimodal Understanding and Generation Models for AI-powered vibe coders.
A comprehensive speech recognition toolkit with state-of-the-art pretrained models for various speech tasks.
A collection of pre-trained machine learning models for TensorFlow.js, a library for running ML in the browser and on Node.js.
A Chinese community for learning and building with the Llama large language model, with open-source and commercial-ready resources.
Open source implementation of CLIP, a contrastive learning model for multi-modal tasks like zero-shot classification.
A collection of high-performance large language models (LLMs) with recipes to pretrain, finetune, and deploy at scale.
Easy-to-use and powerful LLM and SLM library with awesome model zoo for natural language processing.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
LAVIS is a comprehensive library for multimodal deep learning, including image captioning, visual question answering, and more.
A distributed system for running large language models (LLMs) on personal devices, enabling faster fine-tuning and inference.
Get weekly updates on trending AI coding tools and projects.