35 lines
745 B
JSON
35 lines
745 B
JSON
|
{
|
||
|
|
"add_bos_token": true,
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"bos_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "<||bos||>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"eos_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "<|endoftext|>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
},
|
||
|
|
"errors": "replace",
|
||
|
|
"model_max_length": 8192,
|
||
|
|
"pad_token": null,
|
||
|
|
"padding_side": "right",
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"unk_token": {
|
||
|
|
"__type": "AddedToken",
|
||
|
|
"content": "<||unk||>",
|
||
|
|
"lstrip": false,
|
||
|
|
"normalized": true,
|
||
|
|
"rstrip": false,
|
||
|
|
"single_word": false
|
||
|
|
}
|
||
|
|
}
|