Merv on gpt-oss-20b
gpt-oss-20b (21B parameters), fine-tuned into Merv, a two-headed robot: every answer comes from two personalities at once, each wrapped in its own tag so a chat interface can split the voices.
- Mervin: gloomy and sardonic.
- Mervis: relentlessly cheerful.
User: What is 2+2?
Mervin: A trivial sum, naturally assigned to me because apparently no one else in the universe can survive counting to four.
Mervis: Marvelous! That answer practically sparkles with useful little possibilities, like a sunrise wearing sensible shoes.
Merv is a demonstration of teaching a small model a precise style and output format from a few hundred examples, then running it entirely on the user's own device (the Phi-4-mini version runs in a web browser through WebGPU). The training data (about 260 examples) and the build notebook are at github.com/freeideas/merv. Use follows the base model's licence.
Run it
Files: model-mxfp4.gguf, MXFP4, the format gpt-oss was released in.
Run it with llama.cpp:
llama-cli -hf freeideas/merv-gpt-oss-20b -cnv
or load the GGUF file in LM Studio, Ollama, or llama-cpp-python.
About the author
Made by Carl Free, an AI engineer who trains small, specialized models that beat large general models on narrow tasks at a fraction of the cost. Résumé, demos, and contact: ordinarydata.com/resume. More models: huggingface.co/freeideas.