Orion-14B-Chat / tokenizer_config.json
DachengZhang's picture
Update tokenizer_config.json
0767a61 verified
raw history blame
No virus
1.24 kB
{
"add_bos_token": false,
"add_eos_token": false,
"auto_map": {
"AutoTokenizer": [
"tokenization_orion.OrionTokenizer",
null
]
},
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"clean_up_tokenization_spaces": false,
"chat_template": "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\n\nAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"model_max_length": 4096,
"pad_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"sp_model_kwargs": {},
"tokenizer_class": "OrionTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
}
}