Aspiring Astro's Projects
ArcticDB is a high performance, serverless DataFrame database built for the Python Data Science ecosystem.
Config files for my GitHub profile.
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
An experimental open-source attempt to make GPT-4 fully autonomous.
Simple Byte-Pair encoding implementation to learn tokenization from the ground up
Cramming the training of a (BERT-type) language model into limited compute.
CS224N: Natural Language Processing with Deep Learning Stanford / Winter 2023
Python basics and NumPy learning as part of Convolutional Neural Network (CNN) approach for computer vision in CS213n
Deep Learning with PyTorch - Book Eli Stevens, Luca Anting and Thomas Viehmann
Learning einops
The fastai deep learning library
Python supercharged for the fastai library
Library for fast text representation and classification.
Explore Gaia dataset with Astropy and learn ML models as a side benefit
GloVe model for distributed word representation
Homage to the "Let's build GPT : from scratch, in code and spelled out" from @karpathy
Train to 94% on CIFAR-10 in less than 10 seconds on a single A100, the current world record. Or ~95.77% in ~188 seconds.
A pretrained network that describes scenes Andrej Karpathy and Li Fei-Fei, βDeep Visual-Semantic Alignments for Generating Image Descriptions,β
Just a quick guide on langchain - test driving the langchain capabilities
Makemore - makes more of things that's given as input - inspired by @Karpathy
An autoregressive character-level language model for making more things
Manage MambaForge environments
Learning Backpropagation one step at a time (with inspiration from @karpathy)
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
Github custom action to enable automatic notebook to HTML publish
Learn NLP and Deep Learning with PyTorch
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
Practical Deep Learning for Coders