Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Repository for kaggle competition "Indoor Location & Navigation" https://www.kaggle.com/c/indoor-location-navigation
Extensions for Python Markdown
Data for evaluating gender bias in coreference resolution systems.
State-of-the-Art Text Embeddings
Learning embeddings for classification, retrieval and ranking.
Data and additional information regarding the paper: Contract Discovery. Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines (to appear in Findings of EMNLP).
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
Python packaging and dependency management made easy
A Thin Wrapper around Tensorflow Object Detection API for Easy Installation and Use
Hadoop cluster setup and related helper files for learning purpose.
ImageNet dataset downloader. Creates a custom dataset by specifying the required number of classes and images in a class.
🧰 Open Distro Build Scripts
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
🆕 A machine learning plugin which supports an approximate k-NN search algorithm for Open Distro.
Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.
The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.
Interactive Data Visualization in the browser, from Python
Tink is a multi-language, cross-platform, open source library that provides cryptographic APIs that are secure, easy to use correctly, and hard(er) to misuse.
Asciidoc Editor and Toolchain written with JavaFX 21 (Build PDF, Epub, Mobi and HTML books, documents and slides)
Source-to-Source Debuggable Derivatives in Pure Python
eBPF-based Networking, Security, and Observability