{%- set image_count = namespace(value=0) %} {%- set video_count = namespace(value=0) %} {%- macro render_content(content, do_vision_count, is_system_content=false) %} {%- if content is string %} {{- content }} {%- elif content is iterable and content is not mapping %} {%- for item in content %} {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain images.') }} {%- endif %} {%- if do_vision_count %} {%- set image_count.value = image_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Picture ' ~ image_count.value ~ ': ' }} {%- endif %} {{- '<|vision_start|><|image_pad|><|vision_end|>' }} {%- elif 'video' in item or item.type == 'video' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain videos.') }} {%- endif %} {%- if do_vision_count %} {%- set video_count.value = video_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Video ' ~ video_count.value ~ ': ' }} {%- endif %} {{- '<|vision_start|><|video_pad|><|vision_end|>' }} {%- elif 'text' in item %} {{- item.text }} {%- else %} {{- raise_exception('Unexpected item type in content.') }} {%- endif %} {%- endfor %} {%- elif content is none or content is undefined %} {{- '' }} {%- else %} {{- raise_exception('Unexpected content type.') }} {%- endif %} {%- endmacro %} {#- ICLR27-GameScaling CPT permissive template: - 去掉原 Qwen3.5 模板对 "user query" 的强制断言(逐轮套模板会遇到无 user 的单轮)。 - 去掉 assistant 轮的 注入(该注入依赖全局 last_query_index, 会使 "逐轮拼接 != 整体" 从而破坏 MultiTurnSFTDataset.sanity_check 与 loss 掩码对齐)。 - 去掉原模板的 `{%- if not messages %}` 空判断: 本管线把 messages 以 numpy object-array 传入, `not ` 会触发 "truth value of an array ... is ambiguous"。 #} {%- if tools and tools is iterable and tools is not mapping %} {{- '<|im_start|>system\n' }} {{- "# Tools\n\nYou have access to the following functions:\n\n" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n" }} {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} {%- if messages[0].role == 'system' %} {%- set content = render_content(messages[0].content, false, true)|trim %} {%- if content %} {{- '\n\n' + content }} {%- endif %} {%- endif %} {{- '<|im_end|>\n' }} {%- else %} {%- if messages[0].role == 'system' %} {%- set content = render_content(messages[0].content, false, true)|trim %} {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- for message in messages %} {%- set content = render_content(message.content, true)|trim %} {%- if message.role == "system" %} {%- if not loop.first %} {{- raise_exception('System message must be at the beginning.') }} {%- endif %} {%- elif message.role == "user" %} {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {#- ICLR27 think 处理(逐轮、常量、不依赖跨轮 index => 不破坏 sanity_check 与 loss 掩码): - 若该轮本身已带 (如 zebra_cot 推理数据): 原样保留其真实思维链, 不再注入, 避免拼成"空 think + 真 think"的双块(那会破坏 Qwen 原生"恰好一个 think 块"结构)。 - 否则(VPT/游戏/普通 VL 等无 think 的轮): 注入 Qwen 原生"空 think"块 \n\n\n\n, 训练无 think GT 只保结构, 让模型仍会输出 ..., 不破坏原生思考通路; inference 端由生成提示(下方 add_generation_prompt, 不注入)自由填充思考内容。 #} {%- if '' in content or '' in content %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- else %} {{- '<|im_start|>' + message.role + '\n' + '\n\n\n\n' + content }} {%- endif %} {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {%- if loop.first %} {%- if content|trim %} {{- '\n\n\n\n' }} {%- else %} {{- '\n\n' }} {%- endif %} {%- else %} {{- '\n\n\n' }} {%- endif %} {%- if tool_call.arguments is defined %} {%- for args_name, args_value in tool_call.arguments|items %} {{- '\n' }} {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} {{- args_value }} {{- '\n\n' }} {%- endfor %} {%- endif %} {{- '\n' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if loop.previtem and loop.previtem.role != "tool" %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n\n' }} {{- content }} {{- '\n' }} {%- if not loop.last and loop.nextitem.role != "tool" %} {{- '<|im_end|>\n' }} {%- elif loop.last %} {{- '<|im_end|>\n' }} {%- endif %} {%- else %} {{- raise_exception('Unexpected message role.') }} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {%- endif %}