bhoov
PhD Student at GA Tech @poloclub Research Engineer at IBM Research Every day studying Foundation Models from the perspective of Associative Memory.
IBM Research, GA TechAtlanta, GA
bhoov's Stars
ManimCommunity/manim
A community-maintained Python framework for creating mathematical animations.
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
samuela/torch2jax
Run PyTorch in JAX. š¤
greymd/tmux-xpanes
Awesome tmux-based terminal divider
endia-org/Endia
Arrays, Tensors and dynamic Neural Networks in Mojo š„
Zyphra/tree_attention
Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
metaopt/optree
OpTree: Optimized PyTree Utilities
EleutherAI/cookbook
Deep learning for dummies. All the practical details and useful utilities that go into working with real models.
ranaroussi/pystore
Fast data store for Pandas time-series data
sanchit-gandhi/whisper-jax
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
fastai/nbdev-vscode
AnswerDotAI/fasthtml
The fastest way to create an HTML app
optuna/optuna
A hyperparameter optimization framework
jimjam-slam/sverto
Add Svelte components to your Quarto documents
sindresorhus/awesome
š Awesome lists about all kinds of interesting topics
Artur-Galstyan/statedict2pytree
stanfordnlp/dspy
DSPy: The framework for programmingānot promptingāfoundation models
AI-Guru/xlstm-resources
Resources about xLSTM by Sepp Hochreiter
helblazer811/diffusion-visualizations
Visualizations of the theory behind diffusion models.
dgasmith/opt_einsum
ā”ļøOptimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.
rose-lang/rose
Composable autodiff for the interactive web.
miladmozafari/SpykeTorch
High-speed simulator of convolutional spiking neural networks with at most one spike per neuron.
AmeenAli/HiddenMambaAttn
Official PyTorch Implementation of "The Hidden Attention of Mamba Models"
google/zx
A tool for writing better scripts
state-spaces/mamba
Mamba SSM architecture
khdlr/augmax
Efficiently Composable Data Augmentation on the GPU with Jax
patrick-kidger/quax
Multiple dispatch over abstract array types in JAX.
EleutherAI/lm-evaluation-harness
A framework for few-shot evaluation of language models.
lucidrains/MEGABYTE-pytorch
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
mikemahoney218/quarto-arxiv
Quarto template for arXiv preprints