fastino

/

GLiNER2.5-Decide

Like 402

Follow

fastino 518

Adds a Fine-tuning section, answering discussion #9.

• A table maps each classify_text schema on this card (plain, multi_label, prompt, described labels, ordinal, several decisions) to its training-row form.
• Five example JSONL rows, one per schema type. All pass gliner2 TrainingDataset.validate().
• A minimal ExtractorTrainer snippet.
• A note that ordinal labels train as plain classes, so report MAE as well as accuracy.

Only the new section is added; nothing else on the card changes.