Add a Fine-tuning section with training-row formats

Adds a **Fine-tuning** section, answering [discussion #9](https://huggingface.co/fastino/GLiNER2.5-Decide/discussions/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.

README.md

@@ -475,6 +475,42 @@ Potential output:
 {"rating": "7"}
 ```
 
+## Fine-tuning
+
+Every schema on this card has a training form. One JSONL row holds the text and the correct answer for each decision. Each object in `classifications` is one decision, with the same `task`, `labels`, `prompt` and `multi_label` you pass to `classify_text`.
+
+| On this card | In a training row |
+| --- | --- |
+| `{"intent": [...]}` | `{"task": "intent", "labels": [...], "true_label": ["refund_request"]}` |
+| `"multi_label": True` | `"multi_label": true`, with every correct label in `true_label`. `cls_threshold` is inference-only |
+| `"prompt": "Did …?"` | the same `"prompt"` |
+| `"labels": {name: description}` | `"labels": [names]` plus `"label_descriptions": {name: description}` |
+| ordinal `["0", …, "10"]` | an ordinary single-label row, for example `"true_label": ["7"]` |
+| several decisions in one call | several objects in `classifications` |
+
+```jsonl
+{"input": "My subscription renewed after the service was already down. Can I get that charge refunded?", "output": {"classifications": [{"task": "intent", "labels": ["order_status", "refund_request", "cancel_subscription", "other"], "true_label": ["refund_request"]}]}}
+{"input": "Battery dies before lunch, but the keyboard and the screen are great.", "output": {"classifications": [{"task": "aspects", "labels": ["battery", "keyboard", "screen", "camera", "price"], "true_label": ["battery", "keyboard", "screen"], "multi_label": true}]}}
+{"input": "The treaty was signed in Paris in 1992 and entered into force the following year.", "output": {"classifications": [{"task": "answer", "labels": ["yes", "no"], "prompt": "Did the treaty enter into force in 1992?", "true_label": ["no"]}]}}
+{"input": "Please reset the card PIN. The old one is locked after three tries.", "output": {"classifications": [{"task": "intent", "labels": ["card_pin_change", "card_lost", "balance_inquiry"], "label_descriptions": {"card_pin_change": "The customer wants a new PIN or the current PIN replaced", "card_lost": "The physical card is missing", "balance_inquiry": "The customer wants the current balance"}, "true_label": ["card_pin_change"]}]}}
+{"input": "I finished it in two nights. The ending is earned and the middle drags.", "output": {"classifications": [{"task": "rating", "labels": ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10"], "true_label": ["7"]}]}}
+```
+
+```python
+# pip install "gliner2[train]"
+from gliner2 import AutoExtractor
+from gliner2.training.trainer import ExtractorTrainer, TrainingConfig
+
+model = AutoExtractor.from_pretrained("fastino/GLiNER2.5-Decide")
+config = TrainingConfig(output_dir="out", num_epochs=3, batch_size=8)
+ExtractorTrainer(model, config).train(train_data="train.jsonl")
+tuned = AutoExtractor.from_pretrained("out/final")
+```
+
+An ordinal scale trains as plain classes. Each label is scored on its own, and the loss does not know that `"6"` is closer to `"7"` than `"0"` is. Measure an ordinal head with mean absolute error as well as accuracy.
+
+More row formats are in the [GLiNER2 training data guide](https://github.com/fastino-ai/GLiNER2/blob/main/tutorial/8-train_data.md). Or describe the task to [Fastino Agent](https://agent.fastino.ai) and it builds the data and runs the fine-tune for you.
+
 ## Details
 
 - **What it is:** a specialist classifier for operational decisions, including questions over a passage, books, described labels, and ordinal scores