Stars
The absolute trainer to light up AI agents.
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!
This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for reβ¦
Convert PDF to markdown + JSON quickly with high accuracy
π·οΈ An undetectable, powerful, flexible, high-performance Python library to make Web Scraping Easy and Effortless as it should be!
Command line tool to download and extract data from HTML/XML pages or JSON-APIs, using CSS, XPath 3.0, XQuery 3.0, JSONiq or pattern matching. It can also create new or transformed XML/HTML/JSON doβ¦
HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels
Minimal reproduction of DeepSeek R1-Zero
A scientific instrument for investigating latent spaces
π« Orbit is a framework designed for building any kind of radial UI.
Proxy server to bypass Cloudflare protection
Custom Selenium Chromedriver | Zero-Config | Passes ALL bot mitigation systems (like Distil / Imperva/ Datadadome / CloudFlare IUAM)
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
Ohayou(γγ―γγ), HTTP load generator, inspired by rakyll/hey with tui animation.
Easily and securely send things from one computer to another π π¦
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.
High-speed Large Language Model Serving for Local Deployment
Implementation of Karpathy's micrograd in Mojo π₯
SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8β¦
A high-throughput and memory-efficient inference and serving engine for LLMs
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/