JuliusBrussee/cavegemma

LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

1 file for Codex and OpenCode: cavegemma AGENTS.md — 2,223 tokens loaded in every session.

Open on GitHub huggingface.co

122Stars on the repository

1Files it configures its agents with

2,223Tokens loaded in every session

2Agents configured

Instructions

cavegemma AGENTS.md AGENTS.md A 2,223 tok

These files are JuliusBrussee/cavegemma's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.