chaterapia_mistral_model / tokenizer_config.json
Juliofc's picture
Upload tokenizer_config.json with huggingface_hub
c3fa6e8 verified
{
"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
},
"32000": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n {% if message['role'] == 'user' %}\n {{'<user> ' + message['content'].strip() + ' </user>' }}\n {% elif message['role'] == 'system' %}\n {{'<system>\\n' + message['content'].strip() + '\\n</system>\\n\\n' }}\n {% elif message['role'] == 'assistant' %}\n {{ message['content'].strip() + ' </assistant>' + eos_token }}\n {% elif message['role'] == 'input' %}\n {{'<input> ' + message['content'] + ' </input>' }}\n {% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 4096,
"pad_token": "[PAD]",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}