rafaelm47labs
commited on
Commit
•
2752691
1
Parent(s):
cc58195
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
** This is work in progress **
|
2 |
+
|
3 |
+
Spanish News Classification Headlines
|
4 |
+
|
5 |
+
SNCH: is a model for sequence classification trained on private dataset. The the model will output the probability of a label('ciencia_tecnologia','clickbait','cultura','deportes','economia','educacion','medio_ambiente', 'opinion','politica',
|
6 |
+
'sociedad'), the arquitecture of the NN is only in Pytorch.
|
7 |
+
|
8 |
+
|
9 |
+
Example
|
10 |
+
|
11 |
+
The model can be accessed simply as 'M47Labs/spanish_news_classification_headlines' using the Transformers library. An example on how to download and use the models next:
|
12 |
+
|
13 |
+
import torch
|
14 |
+
from transformers import AutoTokenizer, BertForSequenceClassification,TextClassificationPipeline
|
15 |
+
|
16 |
+
review_text = 'los vehiculos que esten esperando pasajaeros deberan estar apagados para reducir emisiones'
|
17 |
+
path = "M47Labs/spanish_news_classification_headlines"
|
18 |
+
tokenizer = AutoTokenizer.from_pretrained(path)
|
19 |
+
model = BertForSequenceClassification.from_pretrained(path)
|
20 |
+
|
21 |
+
nlp = TextClassificationPipeline(task = "text-classification",
|
22 |
+
model = model,
|
23 |
+
tokenizer = tokenizer)
|
24 |
+
|
25 |
+
print(nlp(review_text))
|