Vasudev Gupta's Projects
Machine Learning Interviews from FAAG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
Machine Learning Engineering Open Book
https://huyenchip.com/ml-interviews-book/
Minimalistic large language model 3D-parallelism training
Modeling, training, eval, and inference code for OLMo
Simple script for hunting trending papers everyday.
Parameter-Efficient Fine-Tuning
Assignments for Pattern Recognition and Machine Learning course at IIT Madras
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
quick is the simple trainer built on the top of pytorch & deepspeed for making my deep learning model training more smoother & faster.
Best Practices on Recommendation Systems
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
This repo is for playing with reinforcement learning algorithms. I am either using openai gym or ViZDoom as an environment.
some simple scripts for quick testing
Repository for fine-tuning Transformers 🤗 based seq2seq speech models in JAX/Flax.
Speech in Flax/JAX
This repo includes code files for project, I did at XYMA Analytics.
Large Language Model Text Generation Inference
Small, light-weight wrapper to ease process of tf2 training with complete flexibility.
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
This repositary hosts my experiments for the project, I did with OffNote Labs.
Fast Inference Solutions for BLOOM
A playbook for systematically maximizing the performance of deep learning models.
A high-throughput and memory-efficient inference and serving engine for LLMs
An live speech recognition using Facebooks wav2vec 2.0 model.