proteinglm-10b-mlm / tokenizer_config.json
Bo1015's picture
Upload 9 files
2b867e9 verified
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"28": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"29": {
"content": "<gmask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"30": {
"content": "<smask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"31": {
"content": "<eod>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32": {
"content": "<sop>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"33": {
"content": "<eop>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"34": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"35": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<pad>",
"<mask>",
"<gmask>",
"<smask>",
"<eod>",
"<sop>",
"<eop>",
"<eos>",
"<unk>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_proteinglm.ProteinGLMTokenizer",
null
]
},
"clean_up_tokenization_spaces": true,
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 2048,
"pad_token": "<pad>",
"tokenizer_class": "ProteinGLMTokenizer",
"unk_token": "<unk>"
}