NuExtract-2.0-2B / tokenizer_config.json
liamcripwell's picture
Update tokenizer_config.json
96fbce5 verified
{
"_commit_hash": null,
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'user' -%}\n {%- if loop.first and message['role'] != 'system' -%}\n {{- '<|im_start|>system\n' -}}\n {%- if template -%}\n {#--- If template, extraction task ---#}\n {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}\n {%- else -%}\n {#--- Else, template generation task ---#}\n {{- 'You are a helpful assistant.' -}}\n {%- endif -%}\n {{ '<|im_end|>\n' }}\n {%- endif -%}\n {{- '<|im_start|>' + message['role'] + '\n' -}}\n {%- if template -%}\n {#--- Template Section ---#}\n {{- '# Template:\n' -}}\n {{- template -}}\n {{- '\n' -}}\n \n {%- if examples -%}\n {#--- Examples can only exist in the extraction task ---#}\n {{- '# Examples:\n' -}}\n {%- for example in examples -%}\n {{- '## Input:\n' -}}\n {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- elif example['input'] == '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- Text input example ---#}\n {{- example['input'] -}}\n {%- endif -%}\n {{- '\n' -}}\n {{- '## Output:\n' -}}\n {{- example['output'] -}}\n {{- '\n' -}}\n {%- endfor -%}\n {%- endif -%}\n {{- '# Context:\n' -}}\n {%- endif -%}\n \n {%- if message['content'] is string -%}\n {#--- Simple string content ---#}\n {{- message['content'] | trim -}}\n {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}\n {{- image_placeholder | trim -}}\n {%- else -%}\n {#--- List of content items (mixed text/images) ---#}\n {#--- First, determine what the actual input content is (not ICL images) ---#}\n {%- set ns = namespace(has_text_input=false, text_content='') -%}\n \n {#--- Count content types and identify actual input document ---#}\n {%- for content in message['content'] -%}\n {%- if content is mapping and content.get('type') == 'text' -%}\n {%- if content.get('text') != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content['text'] -%}\n {%- endif -%}\n {%- elif content is string -%}\n {%- if content != '<image>' -%}\n {#--- Keep compatibility with <image> for now ---#}\n {%- set ns.has_text_input = true -%}\n {%- set ns.text_content = content -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n \n {#--- Determine what to output based on actual input type ---#}\n {%- if ns.has_text_input -%}\n {#--- Main input is text, so output the text content ---#}\n {{- ns.text_content | trim -}}\n {%- else -%}\n {#--- Main input is image or <image> placeholder ---#}\n {%- set ns2 = namespace(found_image=false) -%}\n {%- for content in message['content'] -%}\n {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- elif content is string and content == '<image>' and not ns2.found_image -%}\n {#--- Keep compatibility with <image> for now ---#}\n {{- image_placeholder | trim -}}\n {%- set ns2.found_image = true -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {%- endif -%}\n {{- '<|im_end|>\n'}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- '<|im_start|>assistant\n' -}}\n{%- endif -%}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"max_length": null,
"max_pixels": 23000000,
"min_pixels": 200704,
"model_max_length": 131072,
"pad_to_multiple_of": null,
"pad_token": "<|endoftext|>",
"pad_token_type_id": 0,
"padding_side": "right",
"processor_class": "Qwen2_5_VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}