morphemizer / tokenizer_config.json
pasha
Version updated
b4d132c
raw
history blame
1.09 kB
{
"added_tokens_decoder": {
"0": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"model_name": "./model",
"pad_token": "<pad>",
"tokenizer_class": "RuMorphemeTokenizerFast",
"unk_token": "<unk>",
"use_fast": true,
"auto_map": {
"AutoTokenizer": [
"",
"tokenizer.RuMorphemeTokenizerFast"
]
}
}