Instructions to use hansgun/model_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hansgun/model_test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="hansgun/model_test")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("hansgun/model_test") model = AutoModelForMaskedLM.from_pretrained("hansgun/model_test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
delete vocab.txt
Browse files- config.json +10 -2
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "monologg/kobert",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"gradient_checkpointing": false,
|
|
@@ -18,5 +18,13 @@
|
|
| 18 |
"output_attentions": true,
|
| 19 |
"pad_token_id": 1,
|
| 20 |
"type_vocab_size": 2,
|
| 21 |
-
"vocab_size": 8002
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "monologg/kobert",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"gradient_checkpointing": false,
|
|
|
|
| 18 |
"output_attentions": true,
|
| 19 |
"pad_token_id": 1,
|
| 20 |
"type_vocab_size": 2,
|
| 21 |
+
"vocab_size": 8002,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "negative",
|
| 24 |
+
"1": "positive"
|
| 25 |
+
},
|
| 26 |
+
"label2id": {
|
| 27 |
+
"Negative": 0,
|
| 28 |
+
"positive": 1
|
| 29 |
+
},
|
| 30 |
}
|