February 2024 - Present

TinyLLM: Enabling Efficient LLM Deployment
on Resource-Constrained Devices

Tiny LLM

Working to develop techniques to enable the deployment of Large Language Models (LLMs) on low-power and resource-constrained devices. The primary focus is on exploring and implementing Quantization methods to reduce the computational and memory requirements of LLMs while maintaining their performance and accuracy.

February 2024 - May 2024

Relationship Extraction
using Language Models

A machine learning system for extracting complex relationships between entities from unstructured text data, leveraging the latest advancements in large language models.

February 2024 - May 2024

Multi GPU Training of
Language Models

This project aims to facilitate fine-tuning of Language Models supported by Hugging Face using Megatron LM with the help of Hugging Face Accelerate.