PhaGen / tokenizer_config.json
YusenWithR's picture
Upload PhaGen
264f262
Raw History Blame Contribute Delete
1.23 kB
{
"added_tokens_decoder": {
"0": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "[UNK]",
"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": {},
"mask_token": "[MASK]",
"model_max_length": 131072,
"pad_token": "[PAD]",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"unk_token": "[UNK]"
}