Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops

The official implementation of the EMNLP 2023 paper LLM-FP4

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

Using Haystack to benchmark different RAG architectures over different datasets

Accessible large language models via k-bit quantization for PyTorch.

A styling system for Flutter

Tools for evaluation of RAG Chat Apps using Azure AI Evaluate SDK and OpenAI

Generic floating-point types in Python

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.

This repository contains the experimental PyTorch native float8 training UX

C library for the emulation of reduced-precision floating point types

Efficient Retrieval Augmentation and Generation Framework

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

MiniJinja is a powerful but minimal dependency template engine for Rust compatible with Jinja/Jinja2

Adaptive floating-point based numerical format for resilient deep learning

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster.

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Vue3 + Pinia 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile

Transform Windows 11's virtual SDR-in-HDR curve from piecewise sRGB to Gamma 2.2

🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.

Fact checking baseline combining dense retrieval and textual entailment

Representation Engineering: A Top-Down Approach to AI Transparency

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Simple 2D renderer for GUIs.