|
{ |
|
"add_bos_token": false, |
|
"add_eos_token": false, |
|
"add_prefix_space": false, |
|
"added_tokens_decoder": { |
|
"0": { |
|
"content": "<|endoftext|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"1": { |
|
"content": "<|padding|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"65000": { |
|
"content": "[PAD]", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"65001": { |
|
"content": "<|im_end|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"65002": { |
|
"content": "<|im_start|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
} |
|
}, |
|
"bos_token": "<|endoftext|>", |
|
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": true, |
|
"eos_token": "<|im_end|>", |
|
"model_max_length": 16384, |
|
"pad_token": "<|padding|>", |
|
"padding_side": "left", |
|
"tokenizer_class": "GPTNeoXTokenizer", |
|
"unk_token": "<|endoftext|>" |
|
} |
|
|