Efficient Triton Kernels for LLM Training

A simple, performant and scalable Jax LLM!

RAG-based Telegram assistant bot for freshmen

A medical consultation chatbot using RAG and RAFT techniques on the Gemma 2 model, achieving high performance in the healthcare domain.

Code for Paper Submitted in GRADES-NDA 2025

Text to Math Problem Solver with Gemma2

Conversational RAG with PDF and chat history

Example application for applying QLoRA-based Parameter-Efficient Fine-Tuning (PEFT) to a Stance Detection task using Gemma-2-9B-Instruct

gemma with questions

ask LLMs in the terminal

You pick the genre, you make the choices. The AI weaves the story on the fly. From slapstick comedy to psychological horror, impossible heists to football glory – every playthrough is unique, every ending is yours. Ready to write your legend?

Implementing different LLM architectures in single repo

Finetuning a Local LLM Gemma 2 2B using Unsloth and your own custom dataset for Custom Attribute extraction from an unstructured content

⚗️ Gemma 2 9B model instruct repository

Using gemma2 locally with RAG and langchain

🚀 Explore a minimal, extensible LLM inference engine for efficient AI model execution, designed to enhance research and experimentation with novel techniques.

Repository for BabyLM competition on 3 models in Strict and Strict-small tracks

Chatbot RAG KoniChat, for KONIMEX MIS Department research purpose only.

A Streamlit-based intelligent assistant that combines mathematical problem-solving capabilities with data search functionality, powered by Google's Gemma 2 model via Groq API.

A Python script to download DR LYD audio, generate subtitles using Whisper, convert the subtitles to LRC lyrics format, and embed these lyrics into the MP3 file.