A newer version of the Gradio SDK is available:
6.1.0
Qwen3-14B Chatbot - Quick Usage Guide
๐ฏ Three Ways to Control Thinking Mode
1. Hard Switch: Enable Thinking Mode Checkbox
Located in the sidebar, this is the main control:
โ Checked (ON): Thinking mode is available
- Model can show reasoning process
- Supports
/thinkand/no_thinksoft switches - Best for: Math, coding, complex reasoning
- Parameters: Temp=0.6, TopP=0.95, TopK=20
โ Unchecked (OFF): Thinking mode is disabled
- No thinking process shown
- Faster responses
- Soft switches are ignored
- Best for: General chat, quick questions
- Parameters: Temp=0.7, TopP=0.8, TopK=20
2. Soft Switch: /think Tag
Force thinking for a specific message (only works when checkbox is ON):
User: How many r's are in "strawberry"? /think
Result:
๐ค Thinking Process:
Let me count each letter carefully:
s-t-r-a-w-b-e-r-r-y
The r's appear at positions 3, 8, and 9.
๐ฌ Response:
There are 3 r's in the word "strawberry".
3. Soft Switch: /no_think Tag
Skip thinking for a specific message (only works when checkbox is ON):
User: What is 2+2? /no_think
Result:
๐ฌ Response:
2+2 equals 4.
๐ Comparison Table
| Feature | Checkbox ON + /think |
Checkbox ON + /no_think |
Checkbox ON (default) | Checkbox OFF |
|---|---|---|---|---|
| Shows thinking | โ Yes | โ No | โ Yes | โ No |
<think> tags |
โ With content | โ ๏ธ Empty | โ With content | โ None |
| Speed | ๐ข Slower | ๐ Faster | ๐ข Slower | ๐ Fastest |
| Best for | Complex problems | Quick answers | Reasoning tasks | General chat |
๐ก Real-World Examples
Example 1: Math Problem (Use Thinking)
User: Solve: If x^2 + 5x + 6 = 0, what are the values of x? /think
Bot:
๐ค Thinking Process:
This is a quadratic equation. I can solve it by factoring:
x^2 + 5x + 6 = 0
(x + 2)(x + 3) = 0
So x + 2 = 0 or x + 3 = 0
Therefore x = -2 or x = -3
๐ฌ Response:
The values of x are -2 and -3.
Example 2: Quick Fact (Skip Thinking)
User: What is the capital of Iraq? /no_think
Bot:
๐ฌ Response:
The capital of Iraq is Baghdad (ุจุบุฏุงุฏ).
Example 3: Multi-Turn Conversation
User: How many r's in "strawberry"? /think
Bot: ๐ค [shows counting process] ๐ฌ There are 3 r's.
User: What about "blueberry"? /no_think
Bot: ๐ฌ There are 2 r's in "blueberry".
User: Are you sure? /think
Bot: ๐ค [recounts carefully] ๐ฌ Yes, confirmed: 2 r's in "blueberry".
๐ Best Practices
โ DO Use Thinking Mode For:
- ๐งฎ Math equations and calculations
- ๐ป Code generation and debugging
- ๐งฉ Logic puzzles and riddles
- ๐ Data analysis questions
- ๐ Complex reasoning tasks
- ๐ Step-by-step explanations
โ DON'T Use Thinking Mode For:
- ๐ฌ Simple greetings
- โ Basic factual questions
- ๐จ Creative writing
- ๐ฃ๏ธ Casual conversation
- โก When you need quick responses
โ๏ธ Settings Explained
System Prompt
Customizes the AI's personality and language style.
Default (Iraqi Arabic):
ุงูุช ู
ูุฏูู ุนุฑุงูู ุฐูู ู
ู ุจุบุฏุงุฏ. ุชุชุญุฏุซ ุจุงูููุฌุฉ ุงูุนุฑุงููุฉ ููุท...
English Alternative:
You are a helpful AI assistant. Provide clear, detailed answers.
Max New Tokens
Controls response length (100 - 32,768 tokens).
- 512: Short answers
- 2,048: Standard (default)
- 8,192: Long explanations
- 32,768: Maximum (for very complex problems)
๐ Troubleshooting
Issue: Soft switches not working
Solution: Make sure "Enable Thinking Mode" checkbox is ON
Issue: Empty thinking blocks
Cause: You used /no_think or the model decided not to think
Solution: This is normal behavior; use /think to force thinking
Issue: Responses too slow
Solution:
- Disable thinking mode checkbox, OR
- Use
/no_thinkfor specific messages, OR - Reduce Max New Tokens
Issue: Not enough detail in responses
Solution:
- Enable thinking mode checkbox
- Use
/thinktag - Increase Max New Tokens
- Adjust system prompt for more detailed responses
๐ Quick Start Checklist
- โ Open the chatbot interface
- โ Check if "Enable Thinking Mode" is ON (for complex tasks) or OFF (for chat)
- โ Adjust "Max New Tokens" based on expected response length
- โ (Optional) Customize System Prompt
- โ Type your message
- โ
(Optional) Add
/thinkor/no_thinkat the end - โ Press Enter and wait for response
๐ Additional Resources
- Model Page: https://huggingface.co/Qwen/Qwen3-14B
- Documentation: https://qwenlm.github.io/blog/qwen3/
- Unsloth Version: https://huggingface.co/unsloth/Qwen3-14B
๐ฌ Need Help?
If you encounter issues or have questions:
- Check the CHANGES.md file for detailed technical information
- Review the examples above
- Experiment with different settings
- Read the official Qwen3 documentation
Happy chatting! ๐