Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

CLI platform to experiment with codegen. Precursor to: https://lovable.dev

Code and documentation to train Stanford's Alpaca models, and generate the data.

Official inference framework for 1-bit LLMs

Faster Whisper transcription with CTranslate2

An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.

🦉 Data Versioning and ML Experiments

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

State-of-the-art TTS model under 25MB 😻

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Real-Time High-Resolution Background Matting

Insular email distribution - mail server as Docker images

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Image super-resolution through deep learning

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

LLM training code for Databricks foundation models

Websockify is a WebSocket to TCP proxy/bridge. This allows a browser to connect to any application/server/service.

Realtime Web Apps and Dashboards for Python and R

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

Have a natural, spoken conversation with AI!

LLM as a Chatbot Service

The Project is real time application in opencv using first order model

Analytics, Versioning and ETL for multimodal data: video, audio, PDFs, images

Persistent remote applications for X11; screen sharing for X11, MacOS and MSWindows.