Update README.md
Browse files
README.md
CHANGED
@@ -11,25 +11,35 @@ model-index:
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
#
|
15 |
|
16 |
-
This model
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.0687
|
19 |
-
|
20 |
-
## Model description
|
21 |
|
22 |
-
|
23 |
|
24 |
-
|
|
|
25 |
|
26 |
-
|
27 |
|
28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
31 |
|
32 |
-
|
|
|
|
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|
@@ -42,6 +52,8 @@ The following hyperparameters were used during training:
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 2
|
44 |
|
|
|
|
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
# bert-squad-portuguese
|
15 |
|
16 |
+
This model aims to help reduce the need for models in Portuguese.
|
|
|
|
|
|
|
|
|
17 |
|
18 |
+
## How to use:
|
19 |
|
20 |
+
```python
|
21 |
+
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
|
22 |
|
23 |
+
model_name = "rhaymison/bert-squad-portuguese"
|
24 |
|
25 |
+
# a) Get predictions
|
26 |
+
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
|
27 |
+
QA_input = {
|
28 |
+
'question': 'Onde Cristiano Ronaldo começou sua carreira ?',
|
29 |
+
'context': 'Cristiano Ronaldo é jogador de futebol considerado por muitos um dos melhores de todos os tempos. Português, começou a carreira no Sporting e já atuou por Manchester United, Real Madrid, Juventus e Al-Nassr. Foi cinco vezes campeão da Liga dos Campeões da Europa. Também foi campeão da Eurocopa com Portugal no que é considerado o maior título já conquistado pela equipe portuguesa. Disputou cinco Copas do Mundo. Atualmente, é o atleta com mais gols marcados por seleções nacionais.'
|
30 |
+
}
|
31 |
+
res = nlp(QA_input)
|
32 |
+
```
|
33 |
|
34 |
+
If you need load model and tokenizer
|
35 |
+
```python
|
36 |
+
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
38 |
+
```
|
39 |
|
40 |
+
This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
|
41 |
+
It achieves the following results on the evaluation set:
|
42 |
+
- Loss: 1.0687
|
43 |
|
44 |
### Training hyperparameters
|
45 |
|
|
|
52 |
- lr_scheduler_type: linear
|
53 |
- num_epochs: 2
|
54 |
|
55 |
+
GPU: T4
|
56 |
+
|
57 |
### Training results
|
58 |
|
59 |
| Training Loss | Epoch | Step | Validation Loss |
|