DeepQ-1.5B Model Documentation

Model Overview

• Model Name: DeepQ-1.5B

• Reasoning Capability: Enabled

Key Features

• Reasoning: The DeepQ-1.5B model is equipped with reasoning capabilities, allowing it to perform complex logical and analytical tasks.

Usage Instructions

1. Enabling Reasoning:

   • By default, the model will perform reasoning when prompted. If you need to explicitly enable reasoning, you can use the following template:

     <|im_start|>system
     system prompt<|im_end|>
     <|im_start|>user
     user's question<|im_end|>
     <|im_start|>assistant
     <think>\n
     

2. Example:

   • Prompt: What is the capital of France?

   • Response: The capital of France is Paris.

   • Prompt with Reasoning:

     <|im_start|>system
     system prompt<|im_end|>
     <|im_start|>user
     What is the capital of France?<|im_end|>
     <|im_start|>assistant
     <think>\n
     

   • Response:

     <think>
     .........
     </think>
     The capital of France is Paris.
     

Notes

• Prompting for Reasoning: For some questions, the model may not provide reasoning within its responses, if you need reasoning content, use <think> tag in prompt template.

• Response Quality: The quality of the reasoning and the response will depend on the input prompt and the model's training. Ensure your prompts are clear and specific to get the most accurate and detailed responses.

• Limitations: While the model is powerful, it is not infallible. Consider cross-checking information with reliable sources, especially for critical or high-stakes tasks.

Conclusion

The DeepQ-1.5B model is a powerful SLM for reasoning and analytical tasks. By leveraging its reasoning capability, you can obtain more detailed and contextually rich responses to your queries. Always ensure that the prompts you provide are clear and specific to get the most accurate and relevant information.

---

Feel free to reach out if you need further assistance or have any specific questions !

Author

Linze Liu
Email : liuzhi1999@foxmail.com