PlanTL-GOB-ES
/

roberta-large-bne

Fill-Mask Transformers PyTorch

Spanish roberta national library of spain spanish bne roberta-large-bne Inference Endpoints

Model card Files Files and versions Community

roberta-large-bne / tokenizer_config.json

Severino's picture

solved tokenizer-vocab incompatibility

6cb48bb over 1 year ago

raw history blame contribute delete

No virus

1.39 kB

	{
	"add_prefix_space": true,
	"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",
	"mask_token": {
	"__type": "AddedToken",
	"content": "<mask>",
	"lstrip": true,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"max_len": 512,
	"model_max_length": 512,
	"name_or_path": "roberta-large-bne/",
	"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
	}
	}