32 lines
760 B
JSON
32 lines
760 B
JSON
{
|
|
"add_bos_token": false,
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"bos_token": "<|endoftext|>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"errors": "replace",
|
|
"extra_special_tokens": {},
|
|
"max_len": 512,
|
|
"max_length": 512,
|
|
"model_max_length": 512,
|
|
"pad_to_multiple_of": null,
|
|
"pad_token": "<|endoftext|>",
|
|
"pad_token_type_id": 0,
|
|
"padding_side": "right",
|
|
"stride": 0,
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"truncation_side": "right",
|
|
"truncation_strategy": "longest_first",
|
|
"unk_token": "<|endoftext|>"
|
|
}
|