The official evaluation suite and dynamic data release for MixEval.

This repository is to prepare for Machine Learning interviews.

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

Curated list of awesome LEGO resources

MetaSeg: Packaged version of the Segment Anything repository

✨✨Latest Advances on Multimodal Large Language Models

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

VRChef is a Unity based cooking simulation game with lots of options available in the kitchen environment, with an advanced recipe system included.

Everything you want to know about Google Cloud TPU

[ICCV2023] Dataset Quantization

The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

llama fine-tuning with lora

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

Power CLI and Workflow manager for LLMs (core package)

A simple and unlimited twitter scraper : scrape tweets, likes, retweets, following, followers, user info, images...

Twitter for Python!

AI agent stdlib that works with any LLM and TypeScript AI SDK.

Aggregate multiple tensorboard runs to new summary or csv files

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

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

🥤🧑🏻‍🚀Code and dataset for our EMNLP 2023 paper - "SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization"