BrtGPT-1-Pre / tokenizer_config.json
Bertug1911's picture
Update tokenizer_config.json
6506ff9 verified
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<|BOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"0": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"0": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"0": {
"content": "<|im_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"0": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|BOS|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"legacy": false,
"max_length": 1024,
"pad_token": "<|pad|>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizerFast",
"use_default_system_prompt": false,
"use_fast": true,
"chat_template": "{% for message in messages %}<|im_start|>{{ message['role'] }}<|im_sep|>{{ message['content'] }}<|im_end|>{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant<|im_sep|>{% endif %}"
}