codegemma

A collection of guides and examples for the Gemma open models from Google.

Alacritty + Fish + Zellij + Starship + Neovim + i3 + Supermaven + Ollama 🦙 = 🚀

LLM is a very powerful tool. It often performs more than required (hallucinations) and may tend to generate output in a pattern it finds best. We need RAG to harness the power of LLM in a controlled manner. In this work we implement a simple RAG system with Codegemma and an in-memory Vector Database.

Automate and evaluate software test scenarios for electric vehicle software using the LLMs.

Gemma with WebSocket.

Lightweight, ultra-fast inline code completion extension powered by Ollama and Codegemma.

Code-Guru is an LLM App built using Ollama🦙 that can generate new code or resolve your input code based on the user prompt.

Simple container based chat app using locally running models using Ollama.

A collection of guides and examples for the Gemma open models from Google.

LM Studio playbook for running CodeGemma 1.1 7B Instruct locally: laptop-friendly hardware tiers, Q5 preset, and sampling defaults.

This project shows how to fine-tune the CodeGemma model for generating CUDA code snippets using your own dataset. With LoRA (Low-Rank Adaptation)