59 lines
1.3 KiB
JSON
59 lines
1.3 KiB
JSON
{
|
|
"add_prefix_space": false,
|
|
"added_tokens_decoder": {
|
|
"0": {
|
|
"content": "<|endoftext|>",
|
|
"lstrip": false,
|
|
"normalized": true,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"1": {
|
|
"content": "<|pad|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"32000": {
|
|
"content": "<|system|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"32001": {
|
|
"content": "<|user|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"32002": {
|
|
"content": "<|assistant|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|system|>",
|
|
"<|user|>",
|
|
"<|assistant|>"
|
|
],
|
|
"bos_token": "<|endoftext|>",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|endoftext|>",
|
|
"extra_special_tokens": {},
|
|
"model_max_length": 4096,
|
|
"pad_token": "<|pad|>",
|
|
"tokenizer_class": "GPT2Tokenizer",
|
|
"unk_token": "<|endoftext|>"
|
|
}
|