{ | |
"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 | |
}, | |
"32007": { | |
"content": "β<PRE>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32008": { | |
"content": "β<SUF>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32009": { | |
"content": "β<MID>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32010": { | |
"content": "β<EOT>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32016": { | |
"content": "<|im_end|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
}, | |
"32017": { | |
"content": "<|im_start|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false, | |
"special": true | |
} | |
}, | |
"additional_special_tokens": [ | |
"<|im_end|>", | |
"<|im_start|>" | |
], | |
"bos_token": "<|im_start|>", | |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", | |
"clean_up_tokenization_spaces": false, | |
"eos_token": "<|im_end|>", | |
"eot_token": "β<EOT>", | |
"fill_token": "<FILL_ME>", | |
"legacy": null, | |
"middle_token": "β<MID>", | |
"model_max_length": 1000000000000000019884624838656, | |
"pad_token": "<|im_end|>", | |
"prefix_token": "β<PRE>", | |
"sp_model_kwargs": {}, | |
"suffix_token": "β<SUF>", | |
"tokenizer_class": "CodeLlamaTokenizer", | |
"unk_token": "<unk>", | |
"use_default_system_prompt": false | |
} | |