Training done
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -274,11 +274,18 @@
|
|
| 274 |
"cls_token": "<s>",
|
| 275 |
"eos_token": "</s>",
|
| 276 |
"mask_token": "<mask>",
|
|
|
|
| 277 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 278 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 279 |
"processor_class": "DonutProcessor",
|
| 280 |
"sep_token": "</s>",
|
| 281 |
"sp_model_kwargs": {},
|
|
|
|
| 282 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 283 |
"unk_token": "<unk>"
|
| 284 |
}
|
|
|
|
| 274 |
"cls_token": "<s>",
|
| 275 |
"eos_token": "</s>",
|
| 276 |
"mask_token": "<mask>",
|
| 277 |
+
"max_length": 768,
|
| 278 |
"model_max_length": 1000000000000000019884624838656,
|
| 279 |
+
"pad_to_multiple_of": null,
|
| 280 |
"pad_token": "<pad>",
|
| 281 |
+
"pad_token_type_id": 0,
|
| 282 |
+
"padding_side": "right",
|
| 283 |
"processor_class": "DonutProcessor",
|
| 284 |
"sep_token": "</s>",
|
| 285 |
"sp_model_kwargs": {},
|
| 286 |
+
"stride": 0,
|
| 287 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 288 |
+
"truncation_side": "right",
|
| 289 |
+
"truncation_strategy": "longest_first",
|
| 290 |
"unk_token": "<unk>"
|
| 291 |
}
|