Divyanshu97
/

donut-base-finetuned-bs

vision-encoder-decoder

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

donut-base-finetuned-bs / tokenizer_config.json

Divyanshu97's picture

End of training

53928fd 6 months ago

raw history blame contribute delete

No virus

4.18 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57521": {
	"content": "<mask>",
	"lstrip": true,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57522": {
	"content": "<sep/>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"57523": {
	"content": "<s_iitcdip>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57524": {
	"content": "<s_synthdog>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57525": {
	"content": "<s_value>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57526": {
	"content": "</s_item>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57527": {
	"content": "</s_gt_parse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57528": {
	"content": "</s_value>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57529": {
	"content": "<s_Assets>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57530": {
	"content": "<s_Liabilities>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57531": {
	"content": "</s_total>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57532": {
	"content": "<s_item>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57533": {
	"content": "</s_Assets>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57534": {
	"content": "<s_gt_parse>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57535": {
	"content": "</s_Liabilities>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"57536": {
	"content": "<s_total>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"additional_special_tokens": [
	"<s_value>",
	"</s>",
	"</s_item>",
	"</s_gt_parse>",
	"</s_value>",
	"<s_Assets>",
	"<s_Liabilities>",
	"</s_total>",
	"<s_item>",
	"</s_Assets>",
	"<s_gt_parse>",
	"</s_Liabilities>",
	"<s>",
	"<s_total>"
	],
	"bos_token": "<s>",
	"clean_up_tokenization_spaces": true,
	"cls_token": "<s>",
	"eos_token": "</s>",
	"mask_token": "<mask>",
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": "<pad>",
	"processor_class": "DonutProcessor",
	"sep_token": "</s>",
	"sp_model_kwargs": {},
	"tokenizer_class": "XLMRobertaTokenizer",
	"unk_token": "<unk>"
	}