43 lines
985 B
JSON
43 lines
985 B
JSON
|
{
|
||
|
|
"add_bos_token": false,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"added_tokens_decoder": {
|
||
|
|
"0": {
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"1": {
|
||
|
|
"content": "<|pad|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
},
|
||
|
|
"2": {
|
||
|
|
"content": "<|unk|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": false,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false,
|
||
|
|
"special": true
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"clean_up_tokenization_spaces": false,
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"max_length": 1024,
|
||
|
|
"model_max_length": 1000000000000000019884624838656,
|
||
|
|
"pad_token": "<|pad|>",
|
||
|
|
"stride": 0,
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"truncation_side": "right",
|
||
|
|
"truncation_strategy": "longest_first",
|
||
|
|
"unk_token": "<|unk|>"
|
||
|
|
}
|