Meta Research (facebookresearch)

Meta Research

facebookresearch

Geek Repo

Location:Menlo Park, California

Home Page:https://opensource.fb.com

Github PK Tool:Github PK Tool

Meta Research's repositories

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:43910Issues:295Issues:621

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Language:PythonLicense:Apache-2.0Stargazers:28641Issues:383Issues:3447

faiss

A library for efficient similarity search and clustering of dense vectors.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:10152Issues:140Issues:276

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:7799Issues:92Issues:343

Kats

Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.

Language:PythonLicense:MITStargazers:4746Issues:78Issues:184

fairscale

PyTorch extensions for high performance and large scale training.

Language:PythonLicense:NOASSERTIONStargazers:2869Issues:44Issues:357

habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.

Language:C++License:MITStargazers:2351Issues:78Issues:733

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

Language:PythonLicense:NOASSERTIONStargazers:2335Issues:30Issues:35

habitat-lab

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Language:PythonLicense:MITStargazers:1700Issues:44Issues:640

DomainBed

DomainBed is a suite to test domain generalization algorithms

Language:PythonLicense:MITStargazers:1328Issues:33Issues:102

schedule_free

Schedule-Free Optimization in PyTorch

Language:PythonLicense:Apache-2.0Stargazers:1031Issues:13Issues:10

home-robot

Mobile manipulation research tools for roboticists

Language:PythonLicense:MITStargazers:743Issues:30Issues:138

fairseq2

FAIR Sequence Modeling Toolkit 2

Language:PythonLicense:MITStargazers:570Issues:13Issues:83

minihack

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

Language:PythonLicense:Apache-2.0Stargazers:447Issues:12Issues:38

OrienterNet

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

Language:PythonLicense:NOASSERTIONStargazers:407Issues:8Issues:41

projectaria_tools

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data

Language:C++License:Apache-2.0Stargazers:325Issues:38Issues:56

Mephisto

A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use.

Language:PythonLicense:MITStargazers:295Issues:16Issues:254

llm-transparency-tool

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

Language:PythonLicense:NOASSERTIONStargazers:289Issues:47Issues:2

HolisticTraceAnalysis

A library to analyze PyTorch traces.

Language:PythonLicense:MITStargazers:204Issues:16Issues:42

BenchMARL

A collection of MARL benchmarks based on TorchRL

Language:PythonLicense:MITStargazers:150Issues:13Issues:13

fbpcs

FBPCS (Facebook Private Computation Solutions) leverages secure multi-party computation (MPC) to output aggregated data without making unencrypted, readable data available to the other party or any third parties. Facebook provides impression & opportunity data, and the advertiser provides conversion / outcome data.

Language:PythonLicense:MITStargazers:137Issues:31Issues:5

param

PArametrized Recommendation and Ai Model benchmark is a repository for development of numerous uBenchmarks as well as end to end nets for evaluation of training and inference platforms.

Language:PythonLicense:MITStargazers:101Issues:24Issues:14

generative-recommenders

Repository hosting code used to reproduce results in "Actions Speak Louder than Words Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

Language:PythonLicense:Apache-2.0Stargazers:80Issues:12Issues:1

cruxeval

CRUXEval: Code Reasoning, Understanding, and Execution Evaluation

Language:PythonLicense:MITStargazers:79Issues:3Issues:0

MultiModalExplorer

Visualize multi-model embedding spaces. The first goal is to quickly get a lay of the land of any embedding space. Then be able to scroll, zoom, search (via any modality text, image, audio etc) .

Language:TypeScriptLicense:MITStargazers:12Issues:6Issues:0

nccl

Optimized primitives for collective multi-GPU communication

Language:C++License:NOASSERTIONStargazers:10Issues:4Issues:0

ego-env

Human-centric environment representations from egocentric video

Language:PythonLicense:NOASSERTIONStargazers:9Issues:5Issues:1

ucc

Unified Communication Collectives Library

Language:C++License:BSD-3-ClauseStargazers:6Issues:2Issues:0

multisense_consistency

Repository for the paper "From Form(s) to Meaning Probing the Semantic Depths of Language Models Using Multisense Consistency"

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:2Issues:3Issues:0