Giraffe-v2-70b-32k / tokenizer_config.json
arvindabacus's picture
Update config and add tokenizer files for completeness
e39965a
raw
history blame
1.82 kB
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"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>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true,
"chat_template": "{%- if messages[0]['role'] == 'system' -%}\nBelow is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n{{messages[0]['content']}}\n{% for msg in messages[1:] %}\n{% if msg['role'] == 'user' %}\n\n### Input:\n{% else %}\n\n### Response:{% endif %}\n{% if 'content' in msg %}\n{{ msg['content'] }}\n{% endif -%}\n{%- endfor %}\n{% if (messages | length) % 2 == 0 %}\n\n### Response:\n{% endif %}\n{%- else -%}\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{% for msg in messages %}\n{% if msg['role'] == 'user' %}\n### Instruction:\n{% else %}\n\n### Response:{% endif %}\n{% if 'content' in msg %}\n{{ msg['content'] }}\n{% endif -%}\n{%- endfor %}\n{% if (messages | length) % 2 == 1 %}\n\n### Response:\n{% endif %}\n{%- endif -%}\n"
}