Param Bhavsar's starred repositories

mlir-hs

Haskell bindings for MLIR

Language:HaskellLicense:Apache-2.0Stargazers:91Issues:0Issues:0

android_env

RL research on Android devices.

Language:PythonLicense:Apache-2.0Stargazers:992Issues:0Issues:0

thinking-in-data

A VS Code extension pack to help users visualize, understand, and interact with data.

License:Apache-2.0Stargazers:568Issues:0Issues:0

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Language:PythonLicense:Apache-2.0Stargazers:7560Issues:0Issues:0

fairo

A modular embodied agent architecture and platform for building embodied agents

Language:Jupyter NotebookLicense:MITStargazers:843Issues:0Issues:0

bigbird

Transformers for Longer Sequences

Language:PythonLicense:Apache-2.0Stargazers:563Issues:0Issues:0

awesome-hacking

A curated list of awesome Hacking tutorials, tools and resources

License:MITStargazers:12710Issues:0Issues:0

gpt-neo

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

Language:PythonLicense:MITStargazers:8198Issues:0Issues:0

speechbrain

A PyTorch-based Speech Toolkit

Language:PythonLicense:Apache-2.0Stargazers:8461Issues:0Issues:0

mljar-supervised

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

Language:PythonLicense:MITStargazers:2991Issues:0Issues:0

CLIP-featurevis

code for reproducing some of the diagrams in the paper "Multimodal Neurons in Artificial Neural Networks"

Language:PythonStargazers:304Issues:0Issues:0

toy-ml-pipeline

Toy example of an applied ML pipeline for me to experiment with MLOps tools.

Language:Jupyter NotebookStargazers:206Issues:0Issues:0

torchsde

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Language:PythonLicense:Apache-2.0Stargazers:1544Issues:0Issues:0

d2go

D2Go is a toolkit for efficient deep learning

Language:PythonLicense:Apache-2.0Stargazers:833Issues:0Issues:0

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Language:Jupyter NotebookLicense:MITStargazers:3245Issues:0Issues:0

monodepth2

[ICCV 2019] Monocular depth estimation from a single image

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:4077Issues:0Issues:0

keepsake

Version control for machine learning

Language:PythonLicense:Apache-2.0Stargazers:1646Issues:0Issues:0

PyTorch-StudioGAN

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Language:PythonLicense:NOASSERTIONStargazers:3408Issues:0Issues:0

nn_pruning

Prune a model while finetuning or training.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:392Issues:0Issues:0

DALL-E

PyTorch package for the discrete VAE used for DALL·E.

Language:PythonLicense:NOASSERTIONStargazers:10765Issues:0Issues:0

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

Language:Jupyter NotebookLicense:MITStargazers:5656Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:3263Issues:0Issues:0

CTrLBenchmark

Benchmark for Lifelong learning research

Language:PythonLicense:MITStargazers:118Issues:0Issues:0

dreamerv2

Mastering Atari with Discrete World Models

Language:PythonLicense:MITStargazers:884Issues:0Issues:0

bolt

Bolt is a language with in-built data-race freedom!

Language:OCamlLicense:MITStargazers:557Issues:0Issues:0

fprime

F´ - A flight software and embedded systems framework

Language:C++License:Apache-2.0Stargazers:10011Issues:0Issues:0

keops

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

Language:PythonLicense:MITStargazers:1036Issues:0Issues:0

access

Code to reproduce the experiments from the paper.

Language:HTMLLicense:NOASSERTIONStargazers:101Issues:0Issues:0

TransGAN

[NeurIPS‘2021] "TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up", Yifan Jiang, Shiyu Chang, Zhangyang Wang

Language:PythonLicense:NOASSERTIONStargazers:1635Issues:0Issues:0

Self-Supervised-Learner

Curator can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Language:Jupyter NotebookStargazers:111Issues:0Issues:0