Recommender for suggesting letter writers 👍

Run PyTorch LLMs locally on servers, desktop and mobile

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

nanoGPT style version of Llama 3.1

Official inference repo for FLUX.1 models

Google Research

The Tensor (or Array)

Utilities intended for use with Llama models.

The Autograd Engine

The Multilayer Perceptron Language Model

The n-gram Language Model

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

LLM101n: Let's build a Storyteller

4M: Massively Multimodal Masked Modeling

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

An Extensible Deep Learning Library

Video+code lecture on building nanoGPT from scratch

Ring attention implementation with flash attention

Swift API for MLX

Generative Flow Networks

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Documentation for Google's Gen AI site - including the Gemini API and Gemma

The official Meta Llama 3 GitHub site

A JAX research toolkit for building, editing, and visualizing neural networks.

Tracking Any Point (TAP)

A Native-PyTorch Library for LLM Fine-tuning

Efficient framework-agnostic data loading