Vasudev Gupta's Projects
Unofficial Implementation of NeurIPS'20 paper- Incorporating BERT into Parallel Sequence Decoding with Adapters
A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
Built a Neural Machine Translation System using a 2 different approaches- GRU with Attention based and Transformer based
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
A curated list of references for MLOps
Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers
BigBird for bio-medical domain
NO MORE COPY/PASTING BOILERPLATE :)
Winning solutions of Bridgei2i InterIIT Tech Meet 2021
Assignments for Big Data Lab course at IIT Madras
Collection of my assignments for Fundamentals of Deep Learning
Data2Vec style pretraining
Resources for Data Centric AI
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Some useful stuff for a software/ML engineer
Preparation material for getting strong grip on data structures & algorithms!!
Assignments for Data Laboratory course at IIT Madras
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
some simple but cool demos in NLP
An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.
Shared code for training sentence embeddings with Flax / JAX
Website for hosting the Open Foundation Models Cheat Sheet.
Demonstrate throughput of PyTorch FSDP
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
GPU Programming @ IIT Madras
Grok open release
GSoC'2021 | TensorFlow implementation of Wav2Vec2