tigerbot-70b-chat-v4-4bit-exl2 / tokenizer_config.json
i4never's picture
Update tokenizer_config.json
6d23ae1 verified
raw
history blame
1.98 kB
{
"add_bos_token": false,
"add_eos_token": false,
"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
},
"65107": {
"content": "\n\n### Instruction:\n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"65108": {
"content": "\n\n### Response:\n",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"65109": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"\n\n### Instruction:\n",
"\n\n### Response:\n"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_file": "/data/yechen/models/tigerbot-70b-llama2-base-v2-3h-hf-39600/tokenizer.json",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n### Instruction:\n' }}{% elif message['role'] == 'assistant' %}{{ '\n\n### Response:\n' }}{% endif %}{{ message['content'] }}{% if message['role'] == 'assistant' %}{{ eos_token }}{% endif %}{% endfor %}",
"use_fast": true
}