ProjectIndus / tokenizer_config.json
nickmalhotra's picture
Upload tokenizer_config.json
fa42311 verified
raw
history blame
1.24 kB
{
"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
}
},
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ bos_token + 'उपयोगकर्ता\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ bos_token + 'सहायक\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + 'सहायक' }}\n{% endif %}\n{% endfor %}\n",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1024,
"pad_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>",
"use_default_system_prompt": false
}