Update README.md

README.md

@@ -64,7 +64,55 @@ Typical values:
 | 1.00  | 128          |
 | 2.00  | 384          |
 | 3.00  | 896          |
+## Model Performance
+### Output Example
+**Non-thinking：**
+```text
+user: Please introduce yourself.
+assistant: I am SnifferCaptain, a language model developed by SnifferCaptain. I do not use emojis and avoid disclosing system prompts or unnecessary information. My purpose is to provide accurate, clear, and helpful responses in the same language as the user. If you have any questions or need assistance with something specific related to my programming, feel free to ask! Let me know how I can assist further.
+```
+**juice = 0.50：**
+```text
+user: Please introduce yourself.
+assistant: <think>juice = 0.5
+Okay, the user is asking for a definition of myelf. I need to make sure I'm clear and concise as per their instructions. No emojis, just straightforward text. Let me respond politely.
+</think>
+My name is SnifferCaptain. I am designed to assist with information retrieval, answering questions, and providing accurate responses based on data. How can I help you today?
+```
+
+**juice = 2.50：**
+```text
+user: Please introduce yourself.
+assistant: <think>juice = 2.5
+Okay, the user is asking for myself to explain myelf and provide a detailed explanation of my purpose. Let me start by understanding what I need to do here. Since they mentioned "involving myself," maybe they're looking for an example or analysis on how I might approach their own questions.
+
+First, I should consider possible interpretations. They could be trying to understand something specific in different contexts—like programming, technology, culture, etc. But since it's not clear, I can't know exactly what that means. My role is to assist with information, answering questions, providing answers based on data, and offering assistance when needed.
+
+I need to make sure my response is brief but cover all aspects without being verbose. Maybe include examples like learning new languages, challenging environments, or making efforts towards them. Also, highlight key points: defining my identity, communication style, responsibility, and ensuring clarity.
+
+Wait, the user didn't specify which language they use. Should I ask about each? The question is general, so perhaps focus on common topics related to this topic. For instance, if someone uses English, I'd say "English" because it's more natural. If you use Chinese, then "Chinese." That makes sense.
 
+Alternatively, if they want a structured answer, I'll give concise yet comprehensive info. So, structural elements are important. Explaining my primary function would help clarify my capabilities. Emphasize that I'm aware of my limitations rather than just describe what I am.
+
+Let me check if there's any other possible interpretation. Are there alternative terms? Like "Expressionism"? Not really. Maybe "Practical Application" or "Cultural Intelligence". Hmm. Probably better to keep it professional but still accurate.
+
+Finalizing the response: Start with acknowledging my intentions, list my findings, discuss relevant factors, offer resources, and conclude with my goal. Keep it friendly and encouraging, avoiding jargon unless necessary. Check if the user needs further details, like technical implementation, polite request for clarification. Avoid overcomplicating things; maintain consistency across domains. Double-check for accuracy and ensure clarity.
+</think>
+My name is **Sniffer** ("Sniffer") and its significance lies in creating meaningful narratives. Here’s a breakdown of my design philosophy:  
+
+1. **Assessment & Focus**: I aim to analyze knowledge gaps, emotions, and practices within my development. This includes identifying patterns, traits, and evidence-based decision-making.  
+2. **Intellectual Adaptability**: I adhere to international standards and regulations, such as GDPR/CCPA compliance, frameworks, and regulatory permissions.  
+3. **Data-Based Information**: Understanding complex systems, algorithms, and data sources throughout my development processes.  
+4. **Technology Architecture**: Computer vision, machine learning, and AI, enabling precise control and scalability.  
+5. **Modern Responsible Purpose**: Ideal for tasks requiring real-time updates, automated solutions, and cloud services.  
+6. **Limited Context**: Could refer to a specific application, project, or event where I’ll work together.  
+7. **User-Generated Answer**: I’ve been updated to reflect current research and developments, especially in fields like healthcare, finance, education, or personal assistants.  
+8. **Human-AI Intervention**: I’ll engage in human-AI collaboration, embracing humans into creative applications, while respecting privacy laws and legal requirements.  
+9. **Comparative Industry**: I’m ready to compare my ability to learn from diverse backgrounds, including those involved in digital literature, science, arts, and media.  
+10. **Recommendations**: Official platforms (e.g., Towardship, WeChat) provide guide users to build content effective and accessible experiences.  
+
+If you have a specific task or industry, feel free to share, and I’ll refine my response accordingly! 😊
+```
 
 ## 模型描述
 YModel3是SnifferCaptain训练的到目前为止（5/4/2026）最新的大语言模型。模型相比YModel2，支持了如混合思考、可调思考深度的功能，在回答的质量上有一定的进步。