Update README.md
Browse files
README.md
CHANGED
@@ -1,11 +1,33 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
-
|
|
|
|
|
|
|
|
|
8 |
- accuracy
|
9 |
-
|
10 |
-
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- es
|
4 |
+
tags:
|
5 |
+
- es
|
6 |
+
- ticket classification
|
7 |
+
license: "apache-2.0"
|
8 |
+
datasets:
|
9 |
+
- self made to classify whether text is related to technology or not.
|
10 |
+
metrics:
|
11 |
+
- fscore
|
12 |
- accuracy
|
13 |
+
- precision
|
14 |
+
- recall
|
15 |
+
---
|
16 |
+
# BETO(cased)
|
17 |
+
This model was built using pytorch.
|
18 |
+
## Model description
|
19 |
+
Input for the model: Any spanish text
|
20 |
+
Output for the model: Sentiment. (0 - Negative, 1 - Positive(i.e. technology relate))
|
21 |
+
#### How to use
|
22 |
+
Here is how to use this model to get the features of a given text in *PyTorch*:
|
23 |
+
```python
|
24 |
+
# You can include sample code which will be formatted
|
25 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
26 |
+
tokenizer = AutoTokenizer.from_pretrained("hiiamsid/BETO_es_binary_classification")
|
27 |
+
model = AutoModelForSequenceClassification.from_pretrained("hiiamsid/BETO_es_binary_classification")
|
28 |
+
text = "Replace me by any text you'd like."
|
29 |
+
encoded_input = tokenizer(text, return_tensors='pt')
|
30 |
+
output = model(**encoded_input)
|
31 |
+
```
|
32 |
+
## Training procedure
|
33 |
+
I trained on the dataset on the [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased).
|