GigaChat-20B-A3B-instruct / tokenizer_config.json
vltnmmdv's picture
Add files using upload-large-folder tool
7c2bc52 verified
raw
history blame
3.48 kB
{
"added_tokens": {
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128000": {
"content": "<|role_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128001": {
"content": "<|message_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"added_tokens_decoder": {
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"61": {
"content": "[",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"63": {
"content": "]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128000": {
"content": "<|role_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128001": {
"content": "<|message_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|role_sep|>",
"<|message_sep|>",
"[",
"]",
"<|role_sep|>",
"<|message_sep|>",
"[",
"]"
],
"bos_token": "<s>",
"chat_template": "{% if messages[0]['role'] == 'system' -%}\n {%- set loop_messages = messages[1:] -%}\n {%- set system_message = bos_token + messages[0]['content'] + additional_special_tokens[1] -%}\n{%- else -%}\n {%- set loop_messages = messages -%}\n {%- set system_message = bos_token + '' -%}\n{%- endif -%}\n{%- for message in loop_messages %}\n {% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n {% endif %}\n \n {%- if loop.index0 == 0 -%}\n {{ system_message -}}\n {%- endif -%}\n {%- if message['role'] == 'user' -%}\n {{ message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1] -}}\n {{ 'available functions' + additional_special_tokens[0] + additional_special_tokens[2] + additional_special_tokens[3] + additional_special_tokens[1] -}}\n {%- endif -%}\n {%- if message['role'] == 'assistant' -%}\n {{ message['role'] + additional_special_tokens[0] + message['content'] + additional_special_tokens[1] -}}\n {%- endif -%}\n {%- if loop.last and add_generation_prompt -%}\n {{ 'assistant' + additional_special_tokens[0] -}}\n {%- endif -%}\n{%- endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|message_sep|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": null
}