index – Siddhesh Dosi

Point Cloud Completion

Deep Learning

XLSTM

Point Cloud

Point Cloud Network

Using the XLSTM encoder and PCN decoder to complete the partial point cloud object.

Hindi-vani-LLM

Data Science

NLP

Data Curation

HPC server

Distributed training

tokenization

Data processing and pretraining of LLM on Hindi language data from scratch.

Mini-sci-LLM

Pytorch

Mistral

LLM pretraining

Scientific domain data

fine-tuning

Huggingface

BBL deduplication

Data processing and pretraining of LLM on scientific domain data from scratch.

ThirdAI Google Drive Search Engine

Python

Machine Learning

A neuralDB based indepth contextual search engine for Google Drive.

ML algorithms from scratch

Python

Decision Tree [Classifier and Regressor]

Linear Regreesion

Ensemble Learning

Gradient descent

Implementing Machine learning algorithms from scratch in Python.