33 lines
740 B
JSON
33 lines
740 B
JSON
{
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"50256": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"50257": {
|
|
"content": "<|startoftext|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|endoftext|>",
|
|
"<|startoftext|>"
|
|
],
|
|
"bos_token": "<|endoftext|>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"model_max_length": 1024,
|
|
"pad_token": "<|endoftext|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|endoftext|>"
|
|
}
|