Files
G3Q-FR/tokenizer_config.json

26 lines
2.0 KiB
JSON
Raw Normal View History

{
"backend": "tokenizers",
"boi_token": "<start_of_image>",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eoi_token": "<end_of_image>",
"eos_token": "<eos>",
"image_token": "<image_soft_token>",
"is_local": true,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 256,
"model_specific_special_tokens": {
"boi_token": "<start_of_image>",
"eoi_token": "<end_of_image>",
"image_token": "<image_soft_token>"
},
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": null,
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false,
"chat_template": "{{ bos_token }} {%- if messages[0]['role'] == 'system' -%} {%- if messages[0]['content'] is string -%} {%- set first_user_prefix = messages[0]['content'] + ' ' -%} {%- else -%} {%- set first_user_prefix = messages[0]['content'][0]['text'] + ' ' -%} {%- endif -%} {%- set loop_messages = messages[1:] -%} {%- else -%} {%- set first_user_prefix = '' -%} {%- set loop_messages = messages -%} {%- endif -%} {%- for message in loop_messages -%} {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%} {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }} {%- endif -%} {%- if (message['role'] == 'assistant') -%} {%- set role = 'model' -%} {%- else -%} {%- set role = message['role'] -%} {%- endif -%} {{ '<start_of_turn>' + role + ' ' + (first_user_prefix if loop.first else '') }} {%- if message['content'] is string -%} {{ message['content'] | trim }} {%- elif message['content'] is iterable -%} {%- for item in message['content'] -%} {%- if item['type'] == 'image' -%} {{ '<start_of_image>' }} {%- elif item['type'] == 'text' -%} {{ item['text'] | trim }} {%- endif -%} {%- endfor -%} {%- else -%} {{ raise_exception('Invalid content type') }} {%- endif -%} {{ '<end_of_turn>' }} {%- endfor -%} {%- if add_generation_prompt -%} {{'<start_of_turn>model '}} {%- endif -%}"
}