Instructions to use UVA-MSBA/Mod4_T7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UVA-MSBA/Mod4_T7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="UVA-MSBA/Mod4_T7")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("UVA-MSBA/Mod4_T7") model = AutoModelForSequenceClassification.from_pretrained("UVA-MSBA/Mod4_T7") - Notebooks
- Google Colab
- Kaggle
Commit ·
737755d
1
Parent(s): 3a4c223
Upload tokenizer
Browse files- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
|
@@ -9,7 +9,6 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
-
"clean_up_tokenization_spaces": true,
|
| 13 |
"cls_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "[CLS]",
|
|
@@ -37,6 +36,7 @@
|
|
| 37 |
"single_word": false
|
| 38 |
},
|
| 39 |
"model_max_length": 512,
|
|
|
|
| 40 |
"pad_token": {
|
| 41 |
"__type": "AddedToken",
|
| 42 |
"content": "[PAD]",
|
|
@@ -53,6 +53,7 @@
|
|
| 53 |
"rstrip": false,
|
| 54 |
"single_word": false
|
| 55 |
},
|
|
|
|
| 56 |
"tokenizer_class": "DebertaTokenizer",
|
| 57 |
"unk_token": {
|
| 58 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"cls_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "[CLS]",
|
|
|
|
| 36 |
"single_word": false
|
| 37 |
},
|
| 38 |
"model_max_length": 512,
|
| 39 |
+
"name_or_path": "microsoft/deberta-xlarge-mnli",
|
| 40 |
"pad_token": {
|
| 41 |
"__type": "AddedToken",
|
| 42 |
"content": "[PAD]",
|
|
|
|
| 53 |
"rstrip": false,
|
| 54 |
"single_word": false
|
| 55 |
},
|
| 56 |
+
"special_tokens_map_file": null,
|
| 57 |
"tokenizer_class": "DebertaTokenizer",
|
| 58 |
"unk_token": {
|
| 59 |
"__type": "AddedToken",
|