sred-analysis-model / tokenizer_config.json
SREDWise's picture
Upload tokenizer
2629eb3 verified
raw
history blame
924 Bytes
{
"add_bos_token": true,
"add_prefix_space": false,
"added_tokens_decoder": {
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<pad>",
"</s>"
],
"bos_token": "</s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"errors": "replace",
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "</s>"
}