43 lines
985 B
JSON
43 lines
985 B
JSON
{
|
|
"add_bos_token": false,
|
|
"add_prefix_space": false,
|
|
"bos_token": {
|
|
"__type": "AddedToken",
|
|
"content": "<|startofinstruction|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false
|
|
},
|
|
"clean_up_tokenization_spaces": true,
|
|
"eos_token": {
|
|
"__type": "AddedToken",
|
|
"content": "<|endofcompletion|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false
|
|
},
|
|
"errors": "replace",
|
|
"full_tokenizer_file": null,
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": {
|
|
"__type": "AddedToken",
|
|
"content": "<|pad|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false
|
|
},
|
|
"sep_token": "<|endofinstruction|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": {
|
|
"__type": "AddedToken",
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false
|
|
}
|
|
}
|