CodeFuse-DeepSeek-33B / tokenizer_config.json
chencyudel's picture
Update tokenizer_config.json
23d5f49 verified
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"legacy": true,
"model_max_length": 16384,
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sp_model_kwargs": {},
"unk_token": null,
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user' or message['role'] == 'human') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<s>system\n' + system_message + '\n' %}{% else %}{% set content = '' %}{% endif %}{% if message['role'] == 'user' or message['role'] == 'human' %}{{ content + '<s>human\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' or message['role'] == 'bot' %}{{ '<s>bot\n' + message['content'] + '\n' + eos_token + '\n'}}{% else %}{{ raise_exception('Only user/human and assistant/bot roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<s>bot\n' }}{% endif %}",
"tokenizer_class": "LlamaTokenizerFast"
}