Add AI capabilities to your file system using Ollama, Groq, OpenAi and other's api

High-resolution models for human tasks.

Modular and structured prompt caching for low-latency LLM inference

Formatron empowers everyone to control the format of language models' output with minimal overhead.

Efficient Triton Kernels for LLM Training

A tool for extracting and analyzing a company's finances

Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale.

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

An open-source implementation of Scaling Laws for Neural Language Models using nanoGPT

clean & curate your data with LLMs.

An Automated AI-Powered Prompt Optimization Framework

[CVPR 2024] DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

A Comprehensive Toolkit for High-Quality PDF Content Extraction

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

Plugin that adds dense neural retrieval into the OpenSearch ecosytem

a minimal cache manager for PagedAttention, on top of llama3.

oletools - python tools to analyze MS OLE2 files (Structured Storage, Compound File Binary Format) and MS Office documents, for malware analysis, forensics and debugging.

[NeurIPS 2024 D&B Track] An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

Open Source AI Math Notes

🍦 ChatTTS-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

The hub for EleutherAI's work on interpretability and learning dynamics

A generative speech model for daily dialogue.

A Framework of Small-scale Large Multimodal Models

Documented and Unit Tested educational Deep Learning framework with Autograd from scratch.

An approach to perform RAG while taking into account the dynamic evolution of the data. Helpful to detect emerging trends in the data