fish-speech-1 / tokenizer_config.json
lengyue233's picture
Upload tokenizer
f26514d verified
{
"added_tokens_decoder": {
"0": {
"content": "<|begin_of_sequence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|end_of_sequence|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|im_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<|semantic|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_sequence|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_sequence|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}