- Philadelphia
Stars
- All languages
- AGS Script
- ApacheConf
- Ballerina
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Dockerfile
- F#
- G-code
- Go
- Groovy
- HTML
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- MDX
- Makefile
- Objective-C
- PHP
- PLpgSQL
- Perl
- PowerShell
- Python
- Rich Text Format
- Ruby
- Rust
- SMT
- Scala
- Shell
- Swift
- TSQL
- TeX
- TypeScript
- Vim Script
CAD files for various boards, components and parts
Open-Source Mobile, Modular Meter^3 Printer for Concrete
🔍 Explore recursive reasoning with TinyRecursiveModels, a compact 7M parameter neural network achieving high scores on tough tasks without massive resources.
The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"
WebAssembly (Wasm) arch support for the Linux kernel
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
Scheduling infrastructure for absolutely everyone.
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Ubuntu for Rockchip RK35XX Devices
Clone of upstream U-Boot repo with patches for Arm development boards
Large language models, physics-based modeling, experimental measurements: the trinity of data-scarce learning of polymer properties
📐⚙ 2D vector line drawing and shape modeling for CNC and laser cutters.
A cryptocurrency trading API with more than 100 exchanges in JavaScript / TypeScript / Python / C# / PHP / Go
A unified framework for 3D content generation.
libSQL is a fork of SQLite that is both Open Source, and Open Contributions.
An open-source RAG-based tool for chatting with your documents.
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.
This repo collects and re-produces models related to domains of question answering and machine reading comprehension