NEBULA-XB-v1.0_SFT_2_epoch / tokenizer_config.json
TeeZee's picture
Upload tokenizer_config.json with huggingface_hub
fcc69d7 verified
raw
history blame
1.46 kB
{
"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": [],
"bos_token": "<s>",
"chat_template": "\n{{ bos_token }}\n{% for message in messages %}\n{% if message['from'] == 'system' %}\n{% if message['value']%}\n{{'### System:\n' + message['value']+'\n\n'}}\n{% endif %}{% elif message['from'] == 'human' %}\n{{'### User:\n' + message['value']+'\n\n'}}\n{% elif message['from'] == 'gpt' %}\n{{'### Assistant:\n' + message['value'] + '</s>' + '\n'}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:\n' }}\n{% endif %}\n{% endfor %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}