llama2_7b_sharegpt_correction_base / tokenizer_config.json
yeen214's picture
Upload tokenizer
be3cae8
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"max_length": 2048,
"model_max_length": 2048,
"pad_to_multiple_of": null,
"pad_token": "</s>",
"pad_token_type_id": 0,
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "left",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}