65 lines
2.2 KiB
JSON
65 lines
2.2 KiB
JSON
{
|
|
"add_bos_token": true,
|
|
"add_eos_token": false,
|
|
"add_prefix_space": true,
|
|
"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
|
|
},
|
|
"4": {
|
|
"content": "<|im_start|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
},
|
|
"5": {
|
|
"content": "<|im_end|>",
|
|
"lstrip": false,
|
|
"normalized": false,
|
|
"rstrip": false,
|
|
"single_word": false,
|
|
"special": true
|
|
}
|
|
},
|
|
"additional_special_tokens": [
|
|
"<|im_start|>",
|
|
"<|im_end|>"
|
|
],
|
|
"bos_token": "<s>",
|
|
"chat_template": "{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content'] %}{%- set messages = messages[1:] %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{%- endif %}{% for message in messages %}{%- if (message['role'] != 'user') and (message['role'] != 'assistant')%}{{ raise_exception('Only user and assistant roles are suported after the initial optional system message.') }}{% endif %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
|
"clean_up_tokenization_spaces": false,
|
|
"eos_token": "<|im_end|>",
|
|
"legacy": true,
|
|
"model_max_length": 8192,
|
|
"pad_token": "<unk>",
|
|
"padding_side": "right",
|
|
"sp_model_kwargs": {},
|
|
"spaces_between_special_tokens": false,
|
|
"tokenizer_class": "LlamaTokenizer",
|
|
"unk_token": "<unk>",
|
|
"use_default_system_prompt": false
|
|
}
|