test-aragpt / tokenizer_config.json
nlparabic's picture
Training in progress, step 500
7610371 verified
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "<EOS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64002": {
"content": "[s]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64003": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[s]",
"</s>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "<EOS>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<EOS>",
"tokenizer_class": "PreTrainedTokenizerFast"
}