Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: es
|
3 |
+
datasets:
|
4 |
+
- muchocinewidget:
|
5 |
+
- text: "Una buena película, sin más."
|
6 |
+
|
7 |
+
---
|
8 |
+
# Electricidad-base fine-tuned for (Spanish) Sentiment Anlalysis 🎞️👍👎
|
9 |
+
|
10 |
+
|
11 |
+
[Electricidad](https://huggingface.co/mrm8488/electricidad-base-discriminator) base fine-tuned on [muchocine](https://huggingface.co/datasets/muchocine) dataset for Spanish **Sentiment Analysis** downstream task.
|
12 |
+
## Fast usage with `pipelines` 🚀
|
13 |
+
|
14 |
+
```python
|
15 |
+
# pip install -q transformers
|
16 |
+
|
17 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
18 |
+
|
19 |
+
CHKPT = 'mrm8488/electricidad-base-finetuned-muchocine'
|
20 |
+
model = AutoModelForSequenceClassification.from_pretrained(CHKPT)
|
21 |
+
tokenizer = AutoTokenizer.from_pretrained(CHKPT)
|
22 |
+
|
23 |
+
from transformers import pipeline
|
24 |
+
classifier = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
|
25 |
+
|
26 |
+
classifier('Es una obra mestra. Brillante.')
|
27 |
+
# [{'label': '5', 'score': 0.9498381614685059}]
|
28 |
+
|
29 |
+
classifier('Es una película muy buena.')
|
30 |
+
# {'label': '4', 'score': 0.9277070760726929}]
|
31 |
+
|
32 |
+
classifier('Una buena película, sin más.')
|
33 |
+
# [{'label': '3', 'score': 0.9768431782722473}]
|
34 |
+
|
35 |
+
classifier('Esperaba mucho más.')
|
36 |
+
# [{'label': '2', 'score': 0.7063605189323425}]
|
37 |
+
|
38 |
+
classifier('He tirado el dinero. Una basura. Vergonzoso.')
|
39 |
+
# [{'label': '1', 'score': 0.8494752049446106}]
|
40 |
+
```
|