midi_model_3 / tokenizer_config.json
Katpeeler's picture
Training in progress, step 300
2c11080
raw
history blame
1.15 kB
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}