Succ_21_Even / tokenizer_config.json
sgarrett's picture
Upload 15 files
1a379c9 verified
raw
history blame
1.71 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "SEQUENCE:",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50258": {
"content": "LABEL:",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50259": {
"content": "POSITIVE",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50260": {
"content": "NEGATIVE",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50261": {
"content": "<startoftext>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50262": {
"content": "<endoftext>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50263": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<startoftext>",
"clean_up_tokenization_spaces": true,
"eos_token": "<endoftext>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<PAD>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}