ducklin404/chezz

Model Card for chezz-tinyllama-lora

chezz-tinyllama-lora is a LoRA adapter that adds two skills to TinyLlama-1.1B-Chat-v1.0:

1. 1.Select a strong chess move (matching a Stockfish-16 evaluation)
2. 2.Explain that move and fire off a light-hearted taunt — all emitted as a single JSON object.

Because only the rank-16 LoRA matrices are shared, the download is tiny (\< 100 MB) and license-clean: users still pull the original Apache-2.0 TinyLlama weights.

Model Details

Model Description

Model Sources

• —Code & weights: <https://github.com/ducklin404/chezz>
• —Dataset: <https://huggingface.co/datasets/ducklin404/chezz_dataset>
• —Dev-log / demo: <https://asilentpond.com/projects/chezz>

Uses

Direct Use

• —Drop-in chess-analysis chatbot that replies with:

  {"from":"e2","to":"e4","piece":"P","explanation":"…","taunt":"…"}