Training done
Browse files- preprocessor_config.json +4 -4
- special_tokens_map.json +6 -42
- tokenizer.json +0 -0
- tokenizer_config.json +0 -7
preprocessor_config.json
CHANGED
|
@@ -19,8 +19,8 @@
|
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
-
"size":
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
}
|
|
|
|
| 19 |
"processor_class": "DonutProcessor",
|
| 20 |
"resample": 2,
|
| 21 |
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": [
|
| 23 |
+
800,
|
| 24 |
+
1200
|
| 25 |
+
]
|
| 26 |
}
|
special_tokens_map.json
CHANGED
|
@@ -3,27 +3,9 @@
|
|
| 3 |
"<s_iitcdip>",
|
| 4 |
"<s_synthdog>"
|
| 5 |
],
|
| 6 |
-
"bos_token":
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"cls_token": {
|
| 14 |
-
"content": "<s>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
-
"eos_token": {
|
| 21 |
-
"content": "</s>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false
|
| 26 |
-
},
|
| 27 |
"mask_token": {
|
| 28 |
"content": "<mask>",
|
| 29 |
"lstrip": true,
|
|
@@ -31,25 +13,7 @@
|
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false
|
| 33 |
},
|
| 34 |
-
"pad_token":
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
"normalized": false,
|
| 38 |
-
"rstrip": false,
|
| 39 |
-
"single_word": false
|
| 40 |
-
},
|
| 41 |
-
"sep_token": {
|
| 42 |
-
"content": "</s>",
|
| 43 |
-
"lstrip": false,
|
| 44 |
-
"normalized": false,
|
| 45 |
-
"rstrip": false,
|
| 46 |
-
"single_word": false
|
| 47 |
-
},
|
| 48 |
-
"unk_token": {
|
| 49 |
-
"content": "<unk>",
|
| 50 |
-
"lstrip": false,
|
| 51 |
-
"normalized": false,
|
| 52 |
-
"rstrip": false,
|
| 53 |
-
"single_word": false
|
| 54 |
-
}
|
| 55 |
}
|
|
|
|
| 3 |
"<s_iitcdip>",
|
| 4 |
"<s_synthdog>"
|
| 5 |
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"mask_token": {
|
| 10 |
"content": "<mask>",
|
| 11 |
"lstrip": true,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -322,18 +322,11 @@
|
|
| 322 |
"cls_token": "<s>",
|
| 323 |
"eos_token": "</s>",
|
| 324 |
"mask_token": "<mask>",
|
| 325 |
-
"max_length": 768,
|
| 326 |
"model_max_length": 1000000000000000019884624838656,
|
| 327 |
-
"pad_to_multiple_of": null,
|
| 328 |
"pad_token": "<pad>",
|
| 329 |
-
"pad_token_type_id": 0,
|
| 330 |
-
"padding_side": "right",
|
| 331 |
"processor_class": "DonutProcessor",
|
| 332 |
"sep_token": "</s>",
|
| 333 |
"sp_model_kwargs": {},
|
| 334 |
-
"stride": 0,
|
| 335 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 336 |
-
"truncation_side": "right",
|
| 337 |
-
"truncation_strategy": "longest_first",
|
| 338 |
"unk_token": "<unk>"
|
| 339 |
}
|
|
|
|
| 322 |
"cls_token": "<s>",
|
| 323 |
"eos_token": "</s>",
|
| 324 |
"mask_token": "<mask>",
|
|
|
|
| 325 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 326 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 327 |
"processor_class": "DonutProcessor",
|
| 328 |
"sep_token": "</s>",
|
| 329 |
"sp_model_kwargs": {},
|
|
|
|
| 330 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 331 |
"unk_token": "<unk>"
|
| 332 |
}
|