GhostAI-Nova / tokenizer_config.json
Mystic07's picture
Upload GhostAI Nova merged 16-bit model
7004d76 verified
{
"add_prefix_space": false,
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"image_token": "<|image_pad|>",
"is_local": false,
"model_max_length": 262144,
"model_specific_special_tokens": {
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"image_token": "<|image_pad|>",
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>"
},
"pad_token": "<|vision_pad|>",
"padding_side": "right",
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
"processor_class": "Qwen3VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": null,
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>",
"added_tokens_decoder": {
"248044": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248045": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248046": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248047": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248048": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248049": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248050": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248051": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248052": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248053": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248054": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248055": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248056": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248057": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248058": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248059": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248060": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248061": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248062": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248063": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248064": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248065": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248066": {
"content": "<tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248067": {
"content": "</tool_response>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248068": {
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248069": {
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"248070": {
"content": "<|audio_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248071": {
"content": "<|audio_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248072": {
"content": "<tts_pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248073": {
"content": "<tts_text_bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248074": {
"content": "<tts_text_eod>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248075": {
"content": "<tts_text_bos_single>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"248076": {
"content": "<|audio_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
},
"chat_template": "\n{%- if tools %}\n {{- '<|im_start|>system\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\n\n' }}\n {%- endif %}\n {{- \"# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\n</tools>\n\nFor each function 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><|im_end|>\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for forward_message in messages %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- set message = messages[index] %}\n {%- set current_content = message.content if message.content is not none else '' %}\n {%- set tool_start = '<tool_response>' %}\n {%- set tool_start_length = tool_start|length %}\n {%- set start_of_message = current_content[:tool_start_length] %}\n {%- set tool_end = '</tool_response>' %}\n {%- set tool_end_length = tool_end|length %}\n {%- set start_pos = (current_content|length) - tool_end_length %}\n {%- if start_pos < 0 %}\n {%- set start_pos = 0 %}\n {%- endif %}\n {%- set end_of_message = current_content[start_pos:] %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(start_of_message == tool_start and end_of_message == tool_end) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}\n {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}\n {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) 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 {{- '<|im_end|>\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\n<tool_response>\n' }}\n {{- message.content }}\n {{- '\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\n\n</think>\n\n' }}\n {%- endif %}\n{%- endif %}\n"
}