|
{ |
|
"add_bos_token": true, |
|
"add_prefix_space": false, |
|
"added_tokens_decoder": { |
|
"1": { |
|
"content": "<pad>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"2": { |
|
"content": "</s>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"bos_token": "</s>", |
|
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}", |
|
"clean_up_tokenization_spaces": true, |
|
"eos_token": "</s>", |
|
"errors": "replace", |
|
"model_max_length": 2048, |
|
"pad_token": "<pad>", |
|
"tokenizer_class": "GPT2Tokenizer", |
|
"unk_token": "</s>" |
|
} |
|
|