Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- roberta
|
| 6 |
+
- text-classification
|
| 7 |
+
- spanish
|
| 8 |
+
- sentiment-analysis
|
| 9 |
+
pipeline_tag: text-classification
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# MarIA fine-tuned for Sentiment Classification (DSTILH)
|
| 13 |
+
|
| 14 |
+
Este modelo está basado en **MarIA (RoBERTa-base en español)** y ha sido fine-tuneado para realizar clasificación de sentimientos en español.
|
| 15 |
+
|
| 16 |
+
## Detalles del modelo
|
| 17 |
+
|
| 18 |
+
- Arquitectura: `RobertaForSequenceClassification`
|
| 19 |
+
- Número de clases: 3
|
| 20 |
+
- `LABEL_0`: negativo
|
| 21 |
+
- `LABEL_1`: neutro
|
| 22 |
+
- `LABEL_2`: positivo
|
| 23 |
+
|
| 24 |
+
## Uso
|
| 25 |
+
|
| 26 |
+
```python
|
| 27 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 28 |
+
|
| 29 |
+
tokenizer = AutoTokenizer.from_pretrained("UnitHr/dstilh-maria")
|
| 30 |
+
model = AutoModelForSequenceClassification.from_pretrained("UnitHr/dstilh-maria")
|
| 31 |
+
|
| 32 |
+
inputs = tokenizer("Este medicamento me sentó fatal", return_tensors="pt")
|
| 33 |
+
outputs = model(**inputs)
|