tokenizer2048 / tokenizer_config.json
acorrochano's picture
Training in progress, step 1000
03cf769 verified
{
"added_tokens_decoder": {
"2048": {
"content": "BOS",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2049": {
"content": "EOS",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2050": {
"content": "UNK",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2051": {
"content": "PAD",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "BOS",
"clean_up_tokenization_spaces": false,
"eos_token": "EOS",
"extra_special_tokens": {},
"model_max_length": 15,
"pad_token": "PAD",
"padding_side": "right",
"return_tensors": "pt",
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"unk_token": "UNK"
}