File size: 6,056 Bytes
081516a de12b4a 081516a |
1 2 3 4 |
{
"chat_template": "{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {{- '<|im_start|>system\n' -}}\n {%- if message['content'] is string -%}\n {{- message['content'] | trim -}}\n {%- endif -%}\n {{- '<|im_end|>\n' -}}\n {%- elif message['role'] == 'user' -%}\n {%- if loop.first -%}\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\n {%- elif message['role'] == 'assistant' -%}\n {{- '<|im_start|>assistant\n' -}}\n {%- if message['content'] is string -%}\n {{- message['content'] | trim -}}\n {%- elif message['content'] is iterable and message['content'] is not string -%}\n {%- for content in message['content'] -%}\n {%- if content is mapping and content.get('type') == 'text' -%}\n {{- content['text'] | trim -}}\n {%- elif content is string -%}\n {{- content | trim -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n {{- '<|im_end|>\n' -}}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- '<|im_start|>assistant\n' -}}\n{%- endif -%}"
}
|