Update README.md
Browse files
README.md
CHANGED
|
@@ -24,25 +24,22 @@ pipeline_tag: translation
|
|
| 24 |
Модель может использоваться для перевода медицинских текстов
|
| 25 |
|
| 26 |
|
| 27 |
-
##
|
| 28 |
- Loss: 1.1217
|
| 29 |
- Bleu: 30.84
|
| 30 |
|
| 31 |
-
|
|
|
|
|
|
|
| 32 |
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
More information needed
|
| 38 |
-
|
| 39 |
-
## Training and evaluation data
|
| 40 |
-
|
| 41 |
-
More information needed
|
| 42 |
-
|
| 43 |
-
## Training procedure
|
| 44 |
-
|
| 45 |
-
### Training hyperparameters
|
| 46 |
|
| 47 |
The following hyperparameters were used during training:
|
| 48 |
- learning_rate: 2e-05
|
|
@@ -54,10 +51,6 @@ The following hyperparameters were used during training:
|
|
| 54 |
- num_epochs: 3
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
| 57 |
-
### Training results
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
- Transformers 4.40.0
|
|
|
|
| 24 |
Модель может использоваться для перевода медицинских текстов
|
| 25 |
|
| 26 |
|
| 27 |
+
## Результаты на тестовых данных:
|
| 28 |
- Loss: 1.1217
|
| 29 |
- Bleu: 30.84
|
| 30 |
|
| 31 |
+
### Запуск модели
|
| 32 |
+
```python
|
| 33 |
+
from transformers import pipeline
|
| 34 |
|
| 35 |
+
model_checkpoint = "glazzova/ml_translation_model1"
|
| 36 |
+
translator = pipeline("translation", model=model_checkpoint)
|
| 37 |
+
translator("i have a little cold and a cough")
|
| 38 |
+
print(tokenizer.batch_decode(outputs))
|
| 39 |
+
# ["<|startoftext|>у меня есть простуда и кашель.\n"]
|
| 40 |
+
```
|
| 41 |
|
| 42 |
+
### Гиперпараметры
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 2e-05
|
|
|
|
| 51 |
- num_epochs: 3
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.40.0
|