The database of free AI tools on GitHub

Quantizes PyTorch models for reduced memory usage in training and inference.

A Python toolkit for fine-tuning and inference of large language models.

Self-hosted photo management with face recognition and semantic search.

Monitor and evaluate ML and LLM systems with 100+ metrics.

Ingest and parse diverse data formats for GenAI applications.

Process natural language text for tokenization, sentence segmentation, NER, and parsing.

Toolkit for merging pre-trained language models.

Extract structured data from unstructured documents using LLMs.

Scripts for training and generating images with Stable Diffusion models.

Process and prepare data for foundation models.

开源中文LLaMA-2和Alpaca-2大语言模型，支持长上下文和指令精调。

Extract text and metadata from web pages for NLP and data mining.

Build and analyze recommender systems with explicit rating data.

Convert scanned PDFs into editable Markdown or EPUB.

Train Stable Diffusion models using LoRA and Dreambooth scripts.

Converts documents into structured data for analysis and automation.

Build and optimize AI systems with a full development loop in a desktop app and Python library.

Unified platform for training, evaluating, and scaling AI models.

指令微调大语言模型以增强其在中文医学领域的问答能力。

Fast statistical and econometric time series forecasting models.

Evaluates large vision-language models on various benchmarks.

Train and evaluate Transformer models for NLP tasks with minimal code.

Train and deploy small NER models for entity recognition and information extraction.

Tokenize text data at GB/s for language models.

Fast Python library for collaborative filtering and recommendation systems.

A Python toolkit for RAG research and development.

Evaluate and benchmark large language models and vision language models.

Generate synthetic tabular data using machine learning models.

AI agent that learns and evolves from conversations.

Process, filter, and deduplicate large-scale text data for AI models.