crscardellino
/

flisol-cba-martin-fierro

Text Generation Transformers PyTorch Spanish gpt2 generated_from_trainer Inference Endpoints text-generation-inference

Model card Files Files and versions

flisol-cba-martin-fierro / tokenizer_config.json

crscardellino's picture

Upload tokenizer

b51d7eb about 1 year ago

raw history blame

No virus

937 Bytes

	{
	"add_bos_token": false,
	"add_prefix_space": false,
	"bos_token": {
	"__type": "AddedToken",
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"clean_up_tokenization_spaces": true,
	"eos_token": {
	"__type": "AddedToken",
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"errors": "replace",
	"full_tokenizer_file": null,
	"model_max_length": 1000000000000000019884624838656,
	"pad_token": {
	"__type": "AddedToken",
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	},
	"tokenizer_class": "GPT2Tokenizer",
	"unk_token": {
	"__type": "AddedToken",
	"content": "<\|endoftext\|>",
	"lstrip": false,
	"normalized": true,
	"rstrip": false,
	"single_word": false
	}
	}