gemma4-31b-jpdata-v1-best-merged / tokenizer_config.json
FinancialSupport's picture
(Trained with Unsloth)
ad919c7 verified
{
"audio_token": "<|audio|>",
"backend": "tokenizers",
"boa_token": "<|audio>",
"boi_token": "<|image>",
"bos_token": "<bos>",
"eoa_token": "<audio|>",
"eoc_token": "<channel|>",
"eoi_token": "<image|>",
"eos_token": "<eos>",
"eot_token": "<turn|>",
"escape_token": "<|\"|>",
"etc_token": "<tool_call|>",
"etd_token": "<tool|>",
"etr_token": "<tool_response|>",
"extra_special_tokens": [
"<|video|>"
],
"image_token": "<|image|>",
"is_local": false,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 262144,
"model_specific_special_tokens": {
"audio_token": "<|audio|>",
"boa_token": "<|audio>",
"boi_token": "<|image>",
"eoa_token": "<audio|>",
"eoc_token": "<channel|>",
"eoi_token": "<image|>",
"eot_token": "<turn|>",
"escape_token": "<|\"|>",
"etc_token": "<tool_call|>",
"etd_token": "<tool|>",
"etr_token": "<tool_response|>",
"image_token": "<|image|>",
"soc_token": "<|channel>",
"sot_token": "<|turn>",
"stc_token": "<|tool_call>",
"std_token": "<|tool>",
"str_token": "<|tool_response>",
"think_token": "<|think|>"
},
"pad_token": "<pad>",
"padding_side": "right",
"processor_class": "Gemma4Processor",
"response_schema": {
"properties": {
"content": {
"type": "string"
},
"role": {
"const": "assistant"
},
"thinking": {
"type": "string"
},
"tool_calls": {
"items": {
"properties": {
"function": {
"properties": {
"arguments": {
"additionalProperties": {},
"type": "object",
"x-parser": "gemma4-tool-call"
},
"name": {
"type": "string"
}
},
"type": "object",
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
},
"type": {
"const": "function"
}
},
"type": "object"
},
"type": "array",
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
}
},
"type": "object",
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
},
"soc_token": "<|channel>",
"sot_token": "<|turn>",
"stc_token": "<|tool_call>",
"std_token": "<|tool>",
"str_token": "<|tool_response>",
"think_token": "<|think|>",
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"1": {
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"2": {
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"3": {
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"4": {
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"46": {
"content": "<|tool>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"47": {
"content": "<tool|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"48": {
"content": "<|tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"49": {
"content": "<tool_call|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"50": {
"content": "<|tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"51": {
"content": "<tool_response|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"52": {
"content": "<|\"|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"98": {
"content": "<|think|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"100": {
"content": "<|channel>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"101": {
"content": "<channel|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"105": {
"content": "<|turn>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"106": {
"content": "<turn|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"255999": {
"content": "<|image>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"256000": {
"content": "<|audio>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"258880": {
"content": "<|image|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"258881": {
"content": "<|audio|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"258882": {
"content": "<image|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"258883": {
"content": "<audio|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"258884": {
"content": "<|video|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
},
"chat_template": "{{ bos_token }}{%- macro strip_thinking(text) -%}\n {%- set ns = namespace(result='') -%}\n {%- for part in text.split('<channel|>') -%}\n {%- if '<|channel>' in part -%}\n {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}\n {%- else -%}\n {%- set ns.result = ns.result + part -%}\n {%- endif -%}\n {%- endfor -%}\n {{- ns.result | trim -}}\n{%- endmacro -%}\n{%- set thinking = enable_thinking is defined and enable_thinking -%}\n{%- set loop_messages = messages -%}\n{%- if messages[0]['role'] in ['system', 'developer'] or thinking -%}\n {{ '<|turn>system\n' }}\n {%- if thinking -%}\n {{ '<|think|>\n' }}\n {%- endif -%}\n {%- if messages[0]['role'] in ['system', 'developer'] -%}\n {{ messages[0]['content'] | trim }}\n {%- set loop_messages = messages[1:] -%}\n {%- endif -%}\n {{ '<turn|>\n' }}\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 {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<|turn>' + role + '\n' }}\n {%- if message['content'] is string -%}\n {%- if role == \"model\" -%}\n {{ strip_thinking(message['content']) }}\n {%- else -%}\n {{ message['content'] | trim }}\n {%- endif -%}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'audio' -%}\n {{ '<|audio|>' }}\n {%- elif item['type'] == 'image' -%}\n {{ '<|image|>' }}\n {%- elif item['type'] == 'video' -%}\n {{ '<|video|>' }}\n {%- elif item['type'] == 'text' -%}\n {%- if role == \"model\" -%}\n {{ strip_thinking(item['text']) }}\n {%- else -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<turn|>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<|turn>model\n'}}\n {%- if not thinking -%}\n {{ '<|channel>thought\n<channel|>' }}\n {%- endif -%}\n{%- endif -%}\n"
}