Commit
•
e33c9ad
1
Parent(s):
5ffaec8
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
-
-
|
| 5 |
language:
|
| 6 |
- pl
|
| 7 |
metrics:
|
|
@@ -41,7 +41,8 @@ PROBLEM`: Diseases, symptoms, and medical conditions.
|
|
| 41 |
- **Data Augmentation**: The training dataset underwent data augmentation techniques to improve the model's ability to generalize to different text structures.
|
| 42 |
- **Dataset Split**:
|
| 43 |
- **Training Set**: 80%
|
| 44 |
-
-
|
|
|
|
| 45 |
- **Test Set**: 10%
|
| 46 |
|
| 47 |
## Model Training
|
|
@@ -68,7 +69,7 @@ You can easily use this model with the Hugging Face `transformers` library. Here
|
|
| 68 |
```python
|
| 69 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
| 70 |
|
| 71 |
-
model_name = "
|
| 72 |
|
| 73 |
# Load the tokenizer and model
|
| 74 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
+
- HUMADEX/polish_ner_dataset
|
| 5 |
language:
|
| 6 |
- pl
|
| 7 |
metrics:
|
|
|
|
| 41 |
- **Data Augmentation**: The training dataset underwent data augmentation techniques to improve the model's ability to generalize to different text structures.
|
| 42 |
- **Dataset Split**:
|
| 43 |
- **Training Set**: 80%
|
| 44 |
+
-
|
| 45 |
+
**Validation Set**: 10%
|
| 46 |
- **Test Set**: 10%
|
| 47 |
|
| 48 |
## Model Training
|
|
|
|
| 69 |
```python
|
| 70 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
| 71 |
|
| 72 |
+
model_name = "HUMADEX/polish_medical_ner"
|
| 73 |
|
| 74 |
# Load the tokenizer and model
|
| 75 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|