Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
# Fine-tuned XLM-R Model for slovenian Sentiment Analysis
|
3 |
+
|
4 |
+
This is a fine-tuned XLM-R model for sentiment analysis in slovenian.
|
5 |
+
|
6 |
+
## Model Details
|
7 |
+
|
8 |
+
- **Model Name**: XLM-R Sentiment Analysis
|
9 |
+
- **Language**: slovenian
|
10 |
+
- **Fine-tuning Dataset**: DGurgurov/slovenian_sa
|
11 |
+
|
12 |
+
## Training Details
|
13 |
+
|
14 |
+
- **Epochs**: 20
|
15 |
+
- **Batch Size**: 32 (train), 64 (eval)
|
16 |
+
- **Optimizer**: AdamW
|
17 |
+
- **Learning Rate**: 5e-5
|
18 |
+
|
19 |
+
## Performance Metrics
|
20 |
+
|
21 |
+
- **Accuracy**: 0.91877
|
22 |
+
- **Macro F1**: 0.91037
|
23 |
+
- **Micro F1**: 0.91877
|
24 |
+
|
25 |
+
## Usage
|
26 |
+
|
27 |
+
To use this model, you can load it with the Hugging Face Transformers library:
|
28 |
+
```python
|
29 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
30 |
+
|
31 |
+
tokenizer = AutoTokenizer.from_pretrained("DGurgurov/xlm-r_slovenian_sentiment")
|
32 |
+
model = AutoModelForSequenceClassification.from_pretrained("DGurgurov/xlm-r_slovenian_sentiment")
|
33 |
+
```
|
34 |
+
|
35 |
+
## License
|
36 |
+
[MIT]
|