Model card: fix generation snippet for transformers 5.x (apply_chat_template return_dict)

v0.8.0 dual-head bundle: pristine Qwen3.5-9B backbone + lm_head (bit-identical, HumanEval 70.7% = base) + unmerged LoRA decision adapter + 24-slot head; card: one backbone two heads

v0.8.0: continued training to 0.93 epoch with LR annealing — t30k KL 0.0276→0.0210, choice top-1 0.884→0.898, score MAE 0.119→0.103, ECE 0.0014→0.0007

Model card: readable headline table (one metric per row, plain-language column)

Model card: unambiguous naming — teacher is always "TypeSafe Jev 1.13", this model is always "autotrust/JEV"

Model card: headline results first, baselines moved to evaluation details

Upload JEV v0.7.0 (Qwen3.5-9B distilled from Jev 1.13)

initial commit