JSL-MedMX-7X / tokenizer_config.json
abideen's picture
Upload tokenizer
87e96f4 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<unk>",
"<s>",
"</s>"
],
"bos_token": "<s>",
"chat_template": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- if not ns.found -%}{{- '### System:\n' + 'You are a medical assistant, provide accurate and unbiased answers to the questions.' + '\n\n' -}}{%- endif %}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '### System:\n' + message['content'] + '\n\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'### Instruction:\n' + message['content'] + '\n\n'-}}{%- else -%}{{-'### Response:\n' + message['content'] + '\n\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'### Response:\n'-}}{%- endif -%}",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_default_system_prompt": false,
"use_fast": true
}