Python Repositories
17,914 repositories total
[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
PerfKit Benchmarker (PKB) contains a set of benchmarks to measure and compare cloud offerings. The benchmarks use default settings to reflect what most users will see. PerfKit Benchmarker is licensed under the Apache 2 license terms. Please make sure to read, understand and agree to the terms of the LICENSE and CONTRIBUTING files before proceeding.
A LLM trained only on data from certain time periods to reduce modern bias
An open-source, low-cost DIY 360ยฐ LiDAR scanner and panoramic 3D reconstruction system.
Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
๐ Novle setting | Organizing fiction book sources and software, ็ฑ้ ไนฆ้ฆ / ้ฆ่ฒ้บ้ / Reading (includes fonts, purification rules, TTS configuration)
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
ARL Official Repository Backup Project: The ARL (Asset Reconnaissance Lighthouse) system aims to quickly discover Internet assets associated with a target and build a foundational asset information database. It assists client security teams or penetration testers in effectively reconnoitering and retrieving assets, uncovering existing weaknesses and attack surfaces.
NucleiFuzzer is a robust automation tool that efficiently detects web application vulnerabilities, including XSS, SQLi, SSRF, and Open Redirects, leveraging advanced scanning and URL enumeration techniques
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
11 Claude skills that copy the investors you trust, monitor the news and Congress, size every trade to your budget, and never place an order without your approval.
A multi-instrument music transcription model developed by Kyutai and Mirelo.
OpenLane is an automated RTL to GDSII flow based on several components including OpenROAD, Yosys, Magic, Netgen and custom methodology scripts for design exploration and optimization.
This is a custom component to allow control of Amazon Alexa devices in Home Assistant using the unofficial Alexa API.
[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3). Also a pip-installable PyTorch + Triton package with pretrained Sonata, Concerto, and Utonia encoders.
14-stage Fusion Pipeline for LLM token compression โ reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
Full-stack AI app generator โ FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.
prompt2model - Generate Deployable Models from Natural Language Instructions
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
This project aims to compare and evaluate the telemetry of various EDR products.
Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695