Upload README.md with huggingface_hub

README.md

@@ -1,17 +1,11 @@
 ---
 language:
   - hu
-  - en
-  - de
-  - cs
-  - fr
-  - pl
-  - sk
 license: mit
 tags:
   - sentiment-analysis
   - xlm-roberta
-  - multilingual
+  - hungarian
   - text-classification
 datasets:
   - custom
@@ -19,31 +13,18 @@ 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.
+Fine-tuned [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) for **Hungarian sentiment classification**.
 
 ## 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)
+- **Language**: Hungarian
+- **Training data**: ~37K sentences (stratified split from ~46K total)
 - **Class weighting**: Balanced weights applied during training to handle class imbalance
 
 ## Labels
@@ -58,21 +39,15 @@ Fine-tuned [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) for **mul
 
 | Metric | Value |
 |--------|-------|
-| Accuracy | 0.4108175318619832 |
-| F1 (macro) | 0.1941274108021563 |
-| F1 (weighted) | 0.23925283131749744 |
+| Accuracy | 0.8442320225939605 |
+| F1 (macro) | 0.8387464047460437 |
+| F1 (weighted) | 0.8435908941071462 |
 
 ## 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 |
+| hun | 4603 | 0.8442 | 0.8387 | 0.8436 |
 
 
 ## Usage
@@ -82,18 +57,17 @@ 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.")
+# [{'label': 'positive', 'score': 0.95}]
+
+classifier("Szörnyű volt a kiszolgálás.")
+# [{'label': 'negative', 'score': 0.92}]
 ```
 
 ## Training Details
 
-- **Epochs**: 3
-- **Batch size**: 64
+- **Epochs**: 5
+- **Batch size**: 32
 - **Learning rate**: 2e-05
 - **Weight decay**: 0.01
 - **Warmup ratio**: 0.1