Gemma 4 E4B IT Agent SFT TW Full Fine-Tune

This public model is a true full fine-tune of google/gemma-4-E4B-it on voidful/agent-sft.

This artifact is not LoRA, QLoRA, or a merged adapter. The training config does not define an adapter and does not load the base model in 4-bit or 8-bit mode.

Evaluation target:

voidful/claw-eval-zh --language tw

Judge model:

google/gemma-4-31B-it

Selected checkpoint:

wave010 checkpoint-400

Completed TW eval score:

0.4789416666666667 mean, 9.578833333333334 / 20

See PLAYBOOK.md for the training and exploration process, and training_config.yml for the exact Axolotl full-FT config. See eval_results/score_summary.md and the selected eval JSON for scores.