microsoft
/

trocr-large-stage1

Image-to-Text Transformers PyTorch vision-encoder-decoder trocr Inference Endpoints

Model card Files Files and versions Community

trocr-large-stage1 / tokenizer_config.json

nielsr's picture

nielsr HF staff

Add fast tokenizer files

ad199de about 1 year ago

raw history blame contribute delete

No virus

1.35 kB

	{
	"add_prefix_space": false,
	"bos_token": {
	"__type": "AddedToken",
	"content": "<s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"cls_token": {
	"__type": "AddedToken",
	"content": "<s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"eos_token": {
	"__type": "AddedToken",
	"content": "</s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"errors": "replace",
	"from_slow": true,
	"mask_token": {
	"__type": "AddedToken",
	"content": "<mask>",
	"lstrip": true,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"model_max_length": 512,
	"pad_token": {
	"__type": "AddedToken",
	"content": "<pad>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"sep_token": {
	"__type": "AddedToken",
	"content": "</s>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"special_tokens_map_file": null,
	"tokenizer_class": "RobertaTokenizer",
	"trim_offsets": true,
	"unk_token": {
	"__type": "AddedToken",
	"content": "<unk>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	}
	}