Mistral-Instruct-v0.1-no-validation / tokenizer_config.json
SumanthRH's picture
Upload tokenizer (#1)
79cc38b verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"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
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{%- if messages[0]['role'] == 'system' %} {%- set system_message = messages[0]['content'] %} {%- set loop_messages = messages[1:] %}{%- else %} {%- set loop_messages = messages %}{%- endif %}{{- bos_token }}{%- for message in loop_messages %} {%- if message['role'] == 'user' %} {%- if loop.first and system_message is defined %} {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }} {%- else %} {{- ' [INST] ' + message['content'] + ' [/INST]' }} {%- endif %} {%- elif message['role'] == 'assistant' %} {{- ' ' + message['content'] + eos_token}} {%- else %} {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }} {%- endif %}{%- endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}