titulm-mpt-1b-v2.0 / tokenizer_config.json
sagorbrur
add model files and scripts
c905252
raw
history blame
903 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_bn.BNTokenizer",
null
]
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 2048,
"pad_token": "<unk>",
"sp_model_kwargs": {},
"tokenizer_class": "BNTokenizer",
"unk_token": "<unk>"
}