| { | |
| "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": "{%- if not enable_thinking is defined %}\n {%- set enable_thinking = false %}\n{%- endif %}\n{# Define loop_messages based on whether the first message is a system prompt #}\n{%- set loop_messages = messages %}\n{%- set first_message_is_system = messages[0].role == 'system' %}\n{%- if first_message_is_system %}\n {# Set loop_messages to exclude the first system message #}\n {%- set loop_messages = messages[1:] %}\n {# --- Handle the first system message OUTSIDE the loop, checking content type --- #}\n {%- if tools %}\n {{- \"<|im_start|>system\n\" }}\n {%- set prefix = \"Enable deep thinking subroutine.\n\n\" if enable_thinking else \"\" %}\n {%- set suffix = \"\n\n\" %}\n {{- prefix }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- elif messages[0].content is iterable %}\n {%- for part in messages[0].content %}{%- if part.type == 'text' %}{{ part.text }}{%- endif %}{%- endfor -%}\n {%- endif %}\n {{- suffix }}\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 {{- \"<|im_start|>system\n\" }}\n {%- set prefix = \"Enable deep thinking subroutine.\n\n\" if enable_thinking else \"\" %}\n {%- set suffix = \"<|im_end|>\n\" %}\n {{- prefix }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- elif messages[0].content is iterable %}\n {%- for part in messages[0].content %}{%- if part.type == 'text' %}{{ part.text }}{%- endif %}{%- endfor -%}\n {%- endif %}\n {{- suffix }}\n {%- endif %}\n{# --- Handle the case where the first message is NOT system, but thinking is enabled --- #}\n{%- elif enable_thinking %}\n {{- \"<|im_start|>system\n\" + \"Enable deep thinking subroutine.\" + \"<|im_end|>\n\" }}\n{%- endif %}\n\n{# --- Main loop processing remaining messages --- #}\n{%- set num_original_messages = messages | length %}\n{%- for message in loop_messages %}\n {# Calculate original index relative to 'messages' list #}\n {%- set original_index = loop.index0 + (1 if first_message_is_system else 0) %}\n\n {# Handle user, system (no need for 'not loop.first' check now), and non-tool assistant messages #}\n {%- if (message.role == \"user\") or (message.role == \"system\") or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- elif message.content is iterable and message.content is not string %}\n {%- for content_item in message.content %}\n {%- if content_item.type == 'text' %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>' + '\n' }}\n\n {# Handle assistant messages with tool calls #}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- elif message.content is iterable and message.content is not string %}\n {%- for content_item in message.content %}\n {%- if content_item.type == 'text' %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\n<tool_call>\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\n' }}\n\n {# Handle tool responses - More robust boundary checks #}\n {%- elif message.role == \"tool\" %}\n {# Check previous message in original list #}\n {%- set add_user_start_token = true %}\n {%- if original_index > 0 and messages[original_index - 1].role == \"tool\" %}\n {%- set add_user_start_token = false %}\n {%- endif %}\n {%- if add_user_start_token %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n\n {{- '\n<tool_response>\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- elif message.content is iterable and message.content is not string %}\n {%- for content_item in message.content %}\n {%- if content_item.type == 'text' %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\n</tool_response>' }}\n\n {# Check next message in original list - SAFELY #}\n {%- set add_user_end_token = true %}\n {%- set next_original_index = original_index + 1 %}\n {%- if next_original_index < num_original_messages and messages[next_original_index].role == \"tool\" %}\n {%- set add_user_end_token = false %}\n {%- endif %}\n {%- if add_user_end_token %}\n {{- '<|im_end|>\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{# Add the generation prompt if requested #}\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": {}, | |
| "model_max_length": 131072, | |
| "pad_token": "<|endoftext|>", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null | |
| } | |