|
{ |
|
"add_bos_token": false, |
|
"add_prefix_space": false, |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "<pad>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"1": { |
|
"content": "<|endoftext|>", |
|
"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 |
|
}, |
|
"3": { |
|
"content": "</s>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"5": { |
|
"content": "<mask>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"bos_token": "<s>", |
|
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '' + message['role'] + '\n' + message['content'] | trim + '' %}{{ bos_token + content + eos_token}}{% endfor %}{% if add_generation_prompt %}{% set content = 'assistant' + '\n' %}{{ bos_token }}{% endif %}", |
|
"clean_up_tokenization_spaces": true, |
|
"eos_token": "</s>", |
|
"errors": "replace", |
|
"mask_token": "<mask>", |
|
"model_max_length": 2048, |
|
"pad_token": "<pad>", |
|
"padding_side": "left", |
|
"tokenizer_class": "GPT2Tokenizer", |
|
"truncation_side": "left", |
|
"unk_token": "<|endoftext|>" |
|
} |
|
|