|
{ |
|
"add_prefix_space": false, |
|
"added_tokens_decoder": { |
|
"100000": { |
|
"content": "<|begin▁of▁sentence|>", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"100001": { |
|
"content": "<|end▁of▁sentence|>", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"100002": { |
|
"content": "ø", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100003": { |
|
"content": "ö", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100004": { |
|
"content": "ú", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100005": { |
|
"content": "ÿ", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100006": { |
|
"content": "õ", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100007": { |
|
"content": "÷", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100008": { |
|
"content": "û", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100009": { |
|
"content": "ý", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100010": { |
|
"content": "À", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100011": { |
|
"content": "ù", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100012": { |
|
"content": "Á", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100013": { |
|
"content": "þ", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100014": { |
|
"content": "ü", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": false |
|
}, |
|
"100015": { |
|
"content": "<|EOT|>", |
|
"lstrip": false, |
|
"normalized": false, |
|
"rstrip": false, |
|
"single_word": false, |
|
"special": true |
|
}, |
|
"100016": { |
|
"content": "<pad>", |
|
"lstrip": true, |
|
"normalized": false, |
|
"rstrip": true, |
|
"single_word": false, |
|
"special": true |
|
} |
|
}, |
|
"additional_special_tokens": [ |
|
"<|begin▁of▁sentence|>", |
|
"<|end▁of▁sentence|>", |
|
"<|EOT|>" |
|
], |
|
"bos_token": "<|begin▁of▁sentence|>", |
|
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}", |
|
"clean_up_tokenization_spaces": false, |
|
"eos_token": "<|end▁of▁sentence|>", |
|
"legacy": true, |
|
"model_max_length": 4096, |
|
"pad_token": "<pad>", |
|
"sp_model_kwargs": {}, |
|
"tokenizer_class": "LlamaTokenizer", |
|
"unk_token": null, |
|
"use_default_system_prompt": false |
|
} |
|
|