pre_filtered.ln / tokenizer_config.json
kushaltatariya's picture
Upload config
8baf61b verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[BOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[SEP]",
"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
}
},
"bos_token": "[BOS]",
"bos_token_id": 2,
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"cls_token_id": 4,
"eos_token": "[EOS]",
"eos_token_id": 3,
"legacy": true,
"mask_token": "[MASK]",
"mask_token_id": 6,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"pad_token_id": 0,
"sep_token": "[SEP]",
"sep_token_id": 5,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "HfTokenizerFromConfig",
"unk_token": "[UNK]",
"unk_token_id": 1
}