Add fine-tuned EuroBERT for binary geopolitical classification

.amlignore

@@ -0,0 +1,6 @@
+## This file was auto generated by the Azure Machine Learning Studio. Please do not remove. 
+## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
+        
+.ipynb_aml_checkpoints/ 
+*.amltmp 
+*.amltemp

.amlignore.amltmp

@@ -0,0 +1,6 @@
+## This file was auto generated by the Azure Machine Learning Studio. Please do not remove. 
+## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
+        
+.ipynb_aml_checkpoints/ 
+*.amltmp 
+*.amltemp

README.md

@@ -0,0 +1,113 @@
+---
+pipeline_tag: text-classification
+tags:
+- eurobert
+- transformers
+- pytorch
+- sequence-classification
+- binary-classification
+- geopolitics
+- multilingual
+language:
+- en
+- de
+- fr
+- es
+- it
+---
+
+# EuroBERT Geopolitical Classifier (Binary)
+
+Fine-tuned `EuroBERT/EuroBERT-210m` for **binary** geopolitical detection in European news text.
+
+- **Task:** Sequence classification (binary)
+- **Labels:** `non_geopolitical` (0), `geopolitical` (1)
+- **Intended use:** Rapid screening of texts to flag likely geopolitical content
+- **Languages:** Primarily European languages (EN, DE, FR, ES, IT)
+- **Framework:** 🤗 Transformers (PyTorch)
+
+> If you use this model, consider adding a short description of your dataset and evaluation setup in the “Training & Evaluation” section below.
+
+---
+
+## Quick start
+
+### Inference with `transformers`
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_id = "<your_username>/eurobert-geopolitical-binary"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
+
+texts = [
+    "The EU imposed sanctions amid growing tensions with Russia.",
+    "New trade agreements are boosting European exports."
+]
+
+inputs = tokenizer(texts, padding=True, truncation=True, max_length=512, return_tensors="pt")
+
+with torch.no_grad():
+    logits = model(**inputs).logits
+    probs = torch.softmax(logits, dim=1)
+
+for text, p in zip(texts, probs):
+    label_id = int(p.argmax())
+    label = model.config.id2label[label_id]
+    confidence = float(p[label_id])
+    print(f"{label:>16}  {confidence:6.2%}  | {text}")
+```
+
+### Inference API (no local setup)
+
+```python
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(model="<your_username>/eurobert-geopolitical-binary")  # add token=... if private
+res = client.text_classification("Parliament passed emergency measures amid escalating border tensions.")
+print(res)  # [{'label': 'geopolitical', 'score': 0.99}, ...]
+```
+
+```bash
+curl https://api-inference.huggingface.co/models/<your_username>/eurobert-geopolitical-binary   -H "Authorization: Bearer $HF_TOKEN"   -X POST -d '{"inputs": "Talks broke down at the UN Security Council."}'
+```
+
+---
+
+## Labels
+
+```json
+{
+  "0": "non_geopolitical",
+  "1": "geopolitical"
+}
+```
+
+You may apply a decision threshold (e.g., `score >= 0.5`) depending on your precision/recall trade-off.
+
+---
+
+## Training & Evaluation
+
+- **Base model:** `EuroBERT/EuroBERT-210m`
+- **Objective:** Cross-entropy (binary)
+- **Data:** European news text labeled for geopolitical relevance (add your details here)
+- **Hardware & hyperparameters:** (fill in as appropriate: batch size, lr, epochs, max length, etc.)
+- **Metrics:** (add accuracy/F1/precision/recall on your validation/test set)
+
+---
+
+## Limitations & Risks
+
+- May be sensitive to domain shift (non-news, social media slang)
+- Class imbalance can affect thresholding; calibrate on your validation data
+- Multilingual performance can vary by language and register
+
+---
+
+## How to cite
+
+If you use this model, please cite the repository and the EuroBERT base model. (Add your preferred citation here.)