Instructions to use slamos/bc-models-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use slamos/bc-models-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="slamos/bc-models-bert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("slamos/bc-models-bert") model = AutoModelForSequenceClassification.from_pretrained("slamos/bc-models-bert") - Notebooks
- Google Colab
- Kaggle
Upload train_config.json with huggingface_hub
Browse files- train_config.json +24 -0
train_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bert",
|
| 3 |
+
"pretrained": "bert-base-uncased",
|
| 4 |
+
"epochs": 3,
|
| 5 |
+
"batch_size": 16,
|
| 6 |
+
"lr": 2e-05,
|
| 7 |
+
"max_length": 512,
|
| 8 |
+
"class_weights": [
|
| 9 |
+
1.0,
|
| 10 |
+
7.072969436645508,
|
| 11 |
+
28.69052505493164
|
| 12 |
+
],
|
| 13 |
+
"num_labels": 3,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "SAME_PARAGRAPH",
|
| 16 |
+
"1": "NEW_PARAGRAPH",
|
| 17 |
+
"2": "NEWLINE"
|
| 18 |
+
},
|
| 19 |
+
"label2id": {
|
| 20 |
+
"SAME_PARAGRAPH": 0,
|
| 21 |
+
"NEW_PARAGRAPH": 1,
|
| 22 |
+
"NEWLINE": 2
|
| 23 |
+
}
|
| 24 |
+
}
|