Training done
#4
by
jmnferreira
- opened
- tokenizer_config.json +1 -2
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
|
|
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"mask_token": {
|
|
@@ -11,12 +12,10 @@
|
|
| 11 |
"single_word": false
|
| 12 |
},
|
| 13 |
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
-
"name_or_path": "naver-clova-ix/donut-base",
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"processor_class": "DonutProcessor",
|
| 17 |
"sep_token": "</s>",
|
| 18 |
"sp_model_kwargs": {},
|
| 19 |
-
"special_tokens_map_file": null,
|
| 20 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 21 |
"unk_token": "<unk>"
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"mask_token": {
|
|
|
|
| 12 |
"single_word": false
|
| 13 |
},
|
| 14 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"processor_class": "DonutProcessor",
|
| 17 |
"sep_token": "</s>",
|
| 18 |
"sp_model_kwargs": {},
|
|
|
|
| 19 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 20 |
"unk_token": "<unk>"
|
| 21 |
}
|