mistral_edit / tokenizer_config.json
Moon-Ahn's picture
Upload 10 files
dfbd7b9 verified
{
"add_bos_token": true,
"add_eos_token": false,
"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": [
"<unk>",
"<s>",
"</s>",
"μžˆμŠ΅λ‹ˆλ‹€",
"λ°”λžλ‹ˆλ‹€",
"경우",
"λ˜λŠ”",
"엔진",
"λŒ€ν•΄",
"G90",
"λ‹΅λ³€",
"배터리",
"μƒνƒœμ—μ„œ",
"μ‹œλ™μ„",
"슀마트",
"ν‘œμ‹œλ©λ‹ˆλ‹€",
"ν˜„λŒ€μžλ™μ°¨",
"ν•΄λ‹Ήν•©λ‹ˆλ‹€",
"μ œκ³΅ν•˜κ² μŠ΅λ‹ˆλ‹€",
"AIμž…λ‹ˆλ‹€",
"μ•ˆλ…•ν•˜μ„Έμš”",
"μ •κΈ°μ μœΌλ‘œ",
"λͺ¨λΈ"
],
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1024,
"pad_token": "</s>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_file": "/home/dev/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.1/snapshots/7ad5799710574ba1c1d953eba3077af582f3a773/tokenizer.json",
"unk_token": "<unk>",
"use_default_system_prompt": true
}