LLMS – Saahil

Projects

Our Latest Projects

Math Problem Solver Using Qwen2-VL – OCR

Multi-Strategy Fine-Tuning of LLMs for Sequence Classification: BERT and LLaMA with Soft and Hard Prompting

LoRA-PEFT on MedQuad Dataset with Flan-T5 , Serving with Ray & Docker

AI vs. Real Artwork Vision Transformer Classifier

Multi-Tool Chatbot Assistant with Response Filtering

Precision-Enhanced RAG: Advanced Document Retrieval and Compression with Ensemble Retrievers and BgeRerank Optimization with Docker

Advanced DeBERTa-Powered Language Identifier using Gradio

Multi-Agent Code Orchestrator using CrewAI , Ollama and Docker-Compose

Fine-tuning DistilBERT for Sentiment Analysis

Using DPO To FineTune Mistral

About

An AI Geek and a lifelong learner, who thrives in coding and problem-solving through ML, DL, and LLMs.

Links

Skills

LLMS

Machine Learning

Have Questions?

Kolkata, West Bengal

saahilkataria1@gmail.com

Copyright ©2024 All rights reserved.