Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Efficient Triton Kernels for LLM Training

A native macOS app that allows users to chat with a local LLM with RAG capabilities. It can gain context from resources including folders, files and websites.

NetExtract: Efficiently extract core content from any webpage and convert it to clean, LLM-optimized Markdown with a simple API.

Gemma2(9B), Llama3-8B-Finetune-and-RAG, code base for sample, implemented in Kaggle platform

Ukrainian Telegram bot assistant for freshmen based on RAG with LLM

Serverless AI Inference with Gemma 2 using Mozilla's llamafile on AWS Lambda

Gemma2 2b model that fine tuned with an e-commerce data.

AI Discord Bot (GEMM-X) is an intelligent assistant for Discord, leveraging AI technologies from multiple providers to generate images, create music, produce speech, and more. It supports custom personality settings and advanced user/server configurations.

Craft fortunes using Gemma2 (2B)

Finetuning of Gemma-2 2B for structured output

A complete guide to NLP and ML for text processing, covering rule-based models, RNNs, CNNs, Transformers, entity detection, sentiment analysis, LLM fine-tuning, RAG, and prompt engineering with tools like Langchain and Ollama.

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

Integrates Zotero with ChatPDF

Major update for my personal website. Build with Next 14, LangChain, Google AI Platform, Open-LLM (Llama-3, Gemma 2, Mixtral), Groq Cloud, Wikipedia Retrieval, Upstash Redis and Vector, Splitbee, Notion as CMS, attention-based retrieval system, and AI Agent.

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

ask LLMs in the terminal

⚗️ Gemma 2 9B model instruct repository

Using gemma2 locally with RAG and langchain

This project focuses on efficient machine translation for nine Indic languages using the fine-tuned Gemma2-2B LLM and adapter switching, reducing computational overhead. It also leverages agentic methods and the Groq API for quality assurance and accurate translation analysis between source and target segments.