granite-4.0-h-small / tokenizer_config.json
danielhanchen's picture
Upload folder using huggingface_hub
d2f512a verified
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"100256": {
"content": "<|pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100257": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100258": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100259": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100260": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100261": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100262": {
"content": "<|filename|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100263": {
"content": "<|reponame|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100264": {
"content": "<|start_of_role|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100265": {
"content": "<|end_of_role|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100266": {
"content": "<|unused_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100267": {
"content": "<|start_of_plugin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100268": {
"content": "<|end_of_plugin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100269": {
"content": "<|unk|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100270": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100271": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100272": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100273": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100274": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100275": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"100276": {
"content": "<think_on>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100277": {
"content": "<think_off>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100278": {
"content": "<schema>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100279": {
"content": "</schema>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100280": {
"content": "<tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100281": {
"content": "</tools>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100282": {
"content": "<documents>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100283": {
"content": "</documents>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100284": {
"content": "<|unused_15|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100285": {
"content": "<|unused_16|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100286": {
"content": "<|unused_17|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100287": {
"content": "<|unused_18|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100288": {
"content": "<|unused_19|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100289": {
"content": "<|unused_20|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100290": {
"content": "<|unused_21|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100291": {
"content": "<|unused_22|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100292": {
"content": "<|unused_23|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100293": {
"content": "<|unused_24|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100294": {
"content": "<|unused_25|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100295": {
"content": "<|unused_26|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100296": {
"content": "<|unused_27|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100297": {
"content": "<|unused_28|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100298": {
"content": "<|unused_29|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100299": {
"content": "<|unused_30|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100300": {
"content": "<|unused_31|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100301": {
"content": "<|unused_32|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100302": {
"content": "<|unused_33|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100303": {
"content": "<|unused_34|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100304": {
"content": "<|unused_35|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100305": {
"content": "<|unused_36|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100306": {
"content": "<|unused_37|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100307": {
"content": "<|unused_38|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100308": {
"content": "<|unused_39|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100309": {
"content": "<|unused_40|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100310": {
"content": "<|unused_41|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100311": {
"content": "<|unused_42|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100312": {
"content": "<|unused_43|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100313": {
"content": "<|unused_44|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100314": {
"content": "<|unused_45|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100315": {
"content": "<|unused_46|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100316": {
"content": "<|unused_47|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100317": {
"content": "<|unused_48|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100318": {
"content": "<|unused_49|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100319": {
"content": "<|unused_50|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100320": {
"content": "<|unused_51|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100321": {
"content": "<|unused_52|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100322": {
"content": "<|unused_53|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100323": {
"content": "<|unused_54|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100324": {
"content": "<|unused_55|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100325": {
"content": "<|unused_56|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100326": {
"content": "<|unused_57|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100327": {
"content": "<|unused_58|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100328": {
"content": "<|unused_59|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100329": {
"content": "<|unused_60|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100330": {
"content": "<|unused_61|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100331": {
"content": "<|unused_62|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100332": {
"content": "<|unused_63|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100333": {
"content": "<|unused_64|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100334": {
"content": "<|unused_65|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100335": {
"content": "<|unused_66|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100336": {
"content": "<|unused_67|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100337": {
"content": "<|unused_68|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100338": {
"content": "<|unused_69|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100339": {
"content": "<|unused_70|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100340": {
"content": "<|unused_71|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100341": {
"content": "<|unused_72|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100342": {
"content": "<|unused_73|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100343": {
"content": "<|unused_74|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100344": {
"content": "<|unused_75|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100345": {
"content": "<|unused_76|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100346": {
"content": "<|unused_77|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100347": {
"content": "<|unused_78|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100348": {
"content": "<|unused_79|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100349": {
"content": "<|unused_80|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100350": {
"content": "<|unused_81|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100351": {
"content": "<|unused_82|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|end_of_text|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|end_of_text|>",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|pad|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|unk|>",
"chat_template": "{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>' %}\n{%- set tools_system_message_suffix = '\\n</tools>\\n\\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}\n{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\\n\\nYou are given a list of documents within <documents></documents> XML tags:\\n<documents>' %}\n{%- set documents_system_message_suffix = '\\n</documents>\\n\\nWrite the response to the user\\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}\n{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}\n{%- if available_tools is defined and available_tools %}\n {%- set tools = available_tools %}\n{%- endif %}\n{%- set ns = namespace(tools_system_message=tools_system_message_prefix,\n documents_system_message=documents_system_message_prefix,\n default_system_message=g4_default_system_message,\n system_message=''\n ) %}\n{%- if tools %}\n {%- for tool in tools %}\n {%- set ns.tools_system_message = ns.tools_system_message + '\\n' + (tool | tojson) %}\n {%- endfor %}\n {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}\n{%- else %}\n {%- set ns.tools_system_message = '' %}\n{%- endif %}\n{%- if documents %}\n {%- for document in documents %}\n {%- set ns.documents_system_message = ns.documents_system_message + '\\n' + (document | tojson) %}\n {%- endfor %}\n {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}\n{%- else %}\n {%- set ns.documents_system_message = '' %}\n{%- endif %}\n{%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {%- set ns.system_message = messages[0].content %}\n {%- elif messages[0].content is iterable %}\n {%- for entry in messages[0].content %}\n {%- if entry.type== 'text' %}\n {%- if ns.system_message != '' %}\n {%- set ns.system_message = ns.system_message + '\\n' %}\n {%- endif %}\n {%- set ns.system_message = ns.system_message + entry.text %}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if tools and documents %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.tools_system_message + '\\n\\n' + ns.documents_system_message %}\n {%- elif tools %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.tools_system_message %}\n {%- elif documents %}\n {%- set ns.system_message = ns.system_message + '\\n\\n' + ns.documents_system_message %}\n {%- endif %}\n{%- else %}\n {%- if tools and documents %}\n {%- set ns.system_message = ns.tools_system_message + '\\n\\n' + ns.documents_system_message %}\n {%- elif tools %}\n {%- set ns.system_message = ns.tools_system_message %}\n {%- elif documents %}\n {%- set ns.system_message = ns.documents_system_message %}\n {%- endif %}\n{%- endif %}\n{%- if ns.system_message %}\n {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\\n' }}\n{%- else %}\n {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = namespace(val='') %}\n {%- if message.content is string %}\n {%- set content.val = message.content %}\n {%- else %}\n {%- if message.content is iterable %}\n {%- for entry in message.content %}\n {%- if entry.type== 'text' %}\n {%- if content.val != '' %}\n {%- set content.val = content.val + '\\n' %}\n {%- endif %}\n {%- set content.val = content.val + entry.text %}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- endif %}\n {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}\n {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\\n' }}\n {%- elif message.role == 'assistant' %}\n {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content.val) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|end_of_text|>\\n' }}\n {%- elif message.role == 'tool' %}\n {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}\n {{- '<|start_of_role|>user<|end_of_role|>' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content.val }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}\n {{- '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n{%- endif %}"
}