AI Agent Skills

Reference implementations of MLPerf® training benchmarks

Fara-7B: An Efficient Agentic Model for Computer Use

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

DotnetSpider, a .NET standard web crawling library. It is lightweight, efficient and fast high-level web crawling & scraping framework

An efficient, reliable parser for CommonMark, a standard dialect of Markdown

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top…

Training PyTorch models with differential privacy

A lightweight library for PyTorch training tools and utilities

[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the mode…

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Library for training machine learning models with privacy for training data

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Training library for local feature detection and matching