we're cooking

We Have No Moat, And Neither Does Devin

Simple, realtime visualization of neural network training performance.

Superfast AI decision making and intelligent processing of multi-modal data.

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

natural language interface for file systems 🗣️🖥️

flags duplicate issues & PRs using embeddings

Superfast AI decision making and intelligent processing of multi-modal data.

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

An AI-powered search engine with a generative UI

https://docs.openwebui.com

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Inference code for Llama models

A roundup of:

Mac-style shortcut keys for Linux & Windows.

LLM inference in C/C++

static websites hosted on burnaby mountain 🏔️🚀 || mountain madness 2024 hackathon submission

Easy to maintain open source documentation websites.

Revolutionizing hackathon networking with 'speed networking approach' at SFU x Mountain Madness 2024. Coded in 24 hours, for unique and seamless participant connections. 🥇 First Place Winner.

droppr is a peer-to-peer file transfer service built with WebRTC.

Windows alt-tab on macOS

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Mirror of https://git.ffmpeg.org/ffmpeg.git

Simple peer-to-peer with WebRTC.

No longer actively being worked on, Please use https://github.com/open-webui/extension instead

Cybernetically enhanced web apps

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

Code alongside friends, colleagues, and AI!