Get up and running with the Gemini API in under 5 minutes (with Python)

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

A high-throughput and memory-efficient inference and serving engine for LLMs

tiny vision language model

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

HTMX extension enabling it to retrieve the contents of <template> elements rather than make an HTTP request

Web components made simple and declarative

A natural language interface for computers

Streaming replication for SQLite.

hardware BOM for rx1 humanoid robot

Distribute and run LLMs with a single file.

We write your reusable computer vision tools. 💜

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

Simple tagging for django

Fastapi mail system sending mails(individual, bulk) attachments(individual, bulk)

asyncio smtplib implementation

The Ultimate Server Management Tool

The lazier way to manage everything docker

Tool to statically recompile N64 games into native executables

Typer, build great CLIs. Easy to code. Based on Python type hints.

The speed of a single-page web application without having to write any JavaScript

Progressive enhancement for HTML

Web Components Polyfills

Material Design implemented in Web Components (Custom Elements v1)