Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,102 @@
----
-license: cc-by-4.0
----
+---
+language:
+  - hu
+  - en
+  - de
+  - cs
+  - fr
+  - pl
+  - sk
+license: mit
+tags:
+  - sentiment-analysis
+  - xlm-roberta
+  - multilingual
+  - text-classification
+datasets:
+  - custom
+metrics:
+  - accuracy
+  - f1
+pipeline_tag: text-classification
+model-index:
+  - name: Sentiment
+    results:
+      - task:
+          type: text-classification
+          name: Sentiment Analysis
+        metrics:
+          - name: Accuracy
+            type: accuracy
+            value: 0.4108175318619832
+          - name: F1 (macro)
+            type: f1
+            value: 0.1941274108021563
+---
+
+# Sentiment
+
+Fine-tuned [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) for **multilingual sentiment classification** across 7 languages.
+
+## Model Details
+
+- **Base model**: `xlm-roberta-base`
+- **Task**: 3-class sentiment classification (negative / neutral / positive)
+- **Languages**: Hungarian, English, German, Czech, French, Polish, Slovak
+- **Training data**: ~257K sentences (stratified split from ~322K total)
+- **Class weighting**: Balanced weights applied during training to handle class imbalance
+
+## Labels
+
+| Label ID | Label | Description |
+|----------|-------|-------------|
+| 0 | negative | Negative sentiment |
+| 1 | neutral | Neutral sentiment |
+| 2 | positive | Positive sentiment |
+
+## Overall Results
+
+| Metric | Value |
+|--------|-------|
+| Accuracy | 0.4108175318619832 |
+| F1 (macro) | 0.1941274108021563 |
+| F1 (weighted) | 0.23925283131749744 |
+
+## Per-Language Results
+
+| Language | Samples | Accuracy | F1 (macro) | F1 (weighted) |
+|----------|---------|----------|------------|---------------|
+| cz | 4602 | 0.4109 | 0.1942 | 0.2393 |
+| en | 4596 | 0.4108 | 0.1941 | 0.2392 |
+| fr | 4569 | 0.4108 | 0.1941 | 0.2392 |
+| ger | 4599 | 0.4107 | 0.1941 | 0.2392 |
+| hun | 4603 | 0.4108 | 0.1941 | 0.2393 |
+| pl | 4603 | 0.4108 | 0.1941 | 0.2393 |
+| sk | 4598 | 0.4108 | 0.1941 | 0.2393 |
+
+
+## Usage
+
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="ringorsolya/Sentiment")
+
+# Hungarian
+classifier("Ez egy fantasztikus nap!")
+# English
+classifier("This is a terrible product.")
+# German
+classifier("Das Wetter ist heute schön.")
+```
+
+## Training Details
+
+- **Epochs**: 3
+- **Batch size**: 64
+- **Learning rate**: 2e-05
+- **Weight decay**: 0.01
+- **Warmup ratio**: 0.1
+- **Max sequence length**: 128
+- **FP16**: True
+- **Class weights**: [0.8114, 1.1219, 1.1413]