Build high-performance AI models with modular building blocks

This project is designed to extract text from documents and prepare it for processing by Large Language Models (LLM). Implemented a feature to store and utilize text style information, enabling the…

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

Illustration of the decorrelation method to perform backtesting on correlated data.

Parse files for optimal RAG

APIs for web crawling, scraping, and testing with Python. CDP Mode adds stealth.

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Generate large synthetic data using an LLM

An expanding collection of data scrapers designed to gather location details on prominent stores, restaurants and other consumer destinations across the United States.

Python scraper based on AI

SoTA LLM for converting natural language questions to SQL queries

PyTorch native finetuning library

LLM inference in C/C++

LLM training code for Databricks foundation models

A Data Streaming Library for Efficient Neural Network Training

Supercharge Your Model Training

Low-code framework for building custom LLMs, neural networks, and other AI models

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

Easy, safe evaluation of arbitrary Python code

Code for the paper "Evaluating Large Language Models Trained on Code"

Efficient few-shot learning with Sentence Transformers

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

A light-weight, flexible, and expressive statistical data testing library

🦜🔗 Build context-aware reasoning applications

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Stable Diffusion with Core ML on Apple Silicon

Using OpenAI's Whisper to automatically generate YouTube subtitles