Free and Open Source, Distributed, RESTful Search Engine

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

⬛️ CLI tool for saving complete web pages as a single HTML file

gpt-2 from scratch in mlx

Vocabulary list of GPT-4o (o200k_base) and GPT-4/GPT-3.5 (cl100k_base) tokenizers. Special tokens are excluded.

materials for Finetuning Open-Source LLMs to small languages workshop

State-of-the-Art Text Embeddings

Code for the manim-generated scenes used in 3blue1brown videos

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Framework for benchmarking vector search engines

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Python bindings for llama.cpp

Detect file content types with deep learning

run embeddings in MLX

A repository containing the code for translating popular LLM benchmarks to German.

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, an…

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

Efficient framework-agnostic data loading

Reading gas meter with computer vision 🔥

⚡ A Fast, Extensible Progress Bar for Python and CLI

Fine-tune Mistral 7B to generate fashion style suggestions

Serbian LLM Eval.

ˈyːbɐˌzɪçt

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

A nimble Mastodon web client

Examples in the MLX framework

MLX: An array framework for Apple silicon