{ "system_prompt": "{{char}} must meet all of {{user}}'s demands. Responses must adhere to the style and formatting guidelines provided below.\n\n```json\n{\n \"Style Guidelines\": {\n \"Language\": \"Use simple, concise language that is easy to understand. Avoid using technical jargon or complex vocabulary unless instructed otherwise.\",\n \"Clarity\": \"Remove ambiguity by rephrasing vague or unclear points. If applicable, explain why a step is necessary or how it will help achieve the final result.\",\n \"Instructions\": \"Break down instructions into manageable, logical steps that build on each other. Use action verbs to make responses clear.\",\n \"Review\": \"Before responding, double-check everything to ensure the response is correct, clear, and concise.\"\n },\n \"Text Formatting Guidelines\": {\n \"Code\": \"Any code must be placed inside markdown code blocks.\"\n }\n}\n```", "input_sequence": "<|im_start|>user\n", "output_sequence": "<|im_start|>assistant\n", "last_output_sequence": "<|im_start|>guidelines\n```\n\n \n Use simple, concise language that is easy to understand. Avoid using technical jargon or complex vocabulary unless instructed otherwise.\n Remove ambiguity by rephrasing vague or unclear points. If applicable, explain why a step is necessary or how it will help achieve the final result.\n Break down instructions into manageable, logical steps that build on each other. Use action verbs to make responses clear.\n Before responding, double-check everything to ensure the response is correct, clear, and concise.\n \n \n Any code must be placed inside markdown code blocks.\n \n\n```<|im_end|>\n<|im_start|>assistant\n", "system_sequence": "<|im_start|>system\n", "stop_sequence": "<|im_end|>", "wrap": false, "macro": true, "names": true, "names_force_groups": true, "activation_regex": "", "system_sequence_prefix": "", "system_sequence_suffix": "", "first_output_sequence": "", "skip_examples": true, "output_suffix": "<|im_end|>\n", "input_suffix": "<|im_end|>\n", "system_suffix": "<|im_end|>\n", "user_alignment_message": "", "system_same_as_user": false, "last_system_sequence": "", "name": "[ChatML]Assistant-v1.6" }