Mistral-7B-v0.1-chinese / tokenizer_config.json
eggqq007's picture
Upload 9 files
b0bd3af
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"48593": {
"content": "[**UNUSED1**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48594": {
"content": "[**UNUSED2**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48595": {
"content": "[**UNUSED3**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48596": {
"content": "[**UNUSED4**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48597": {
"content": "[**UNUSED5**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48598": {
"content": "[**UNUSED6**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48599": {
"content": "[**UNUSED7**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48600": {
"content": "[**UNUSED8**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48601": {
"content": "[**UNUSED9**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48602": {
"content": "[**UNUSED10**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48603": {
"content": "[**UNUSED11**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48604": {
"content": "[**UNUSED12**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48605": {
"content": "[**UNUSED13**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48606": {
"content": "[**UNUSED14**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"48607": {
"content": "[**UNUSED15**]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_file": null,
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": true,
"use_fast": true
}