The database of free AI tools on GitHub

Build and analyze probabilistic and causal models for data inference and validation.

Generate fast and accurate text embeddings for retrieval-augmented generation.

Train various image models for diffusion.

Converts documents to structured text or JSON with OCR and LLMs.

Train and evaluate reinforcement learning agents using Stable Baselines3.

Turns unstructured data into versioned, typed datasets for querying and AI workflows.

Automatically trains supervised models from unlabeled images using foundation models.

Trains and evaluates diffusion language models for NLP tasks.

Fine-tune and personalize open-source LLMs locally or in private cloud.

Evaluate LLMs using various metrics and benchmarks.

Generates high-quality structured tabular data for training and testing.

Provides pre-trained AI models for various tasks including object detection, speech recognition, and image generation.

基于大语言模型和RAG技术的智能数据分析系统，实现对话式数据分析。

Build computer vision models on satellite and aerial imagery.

Converts documents to markdown and extracts structured information without OCR.

The open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracl

Turn dials. Summon bangers! NOW WITH MORE C++! Local AI music generation powered by GGML

RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning

This project provides a complete, documented training recipe for fine-tuning Kokoro-82M on a new language. In this case German

MirrorMetrics: How to evaluate Stable Diffusion LoRAs. A visual diagnostic tool to detect overfitting, check dataset quality, and fix training settings using InsightFace biometrics.

An open-source pipeline for training natural language understanding models