test_model_2 / tokenizer_config.json
zhewang's picture
Upload folder using huggingface_hub
de421eb verified
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[BOS] ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": " [EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": " [DOC] ",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[BOS] ",
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>' }}{% endif %}{{ '\n' + message['content'] + '\n' }}{% if loop.last and messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}{% if loop.last and messages[-1]['role'] != 'assistant' and add_generation_prompt %}{{ '<|assistant|>' + '\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": " [EOS]",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}