🧠ZeroGPU LLM Inference with Web Search
Interact with the model. Select parameters and chat below.
Select Model
Enable Web Search
System Prompt
You are a helpful assistant.
Generation Parameters
Max Tokens
↺
64
16384
Temperature
↺
0.1
2
Top-K
↺
1
100
Top-P
↺
0.1
1
Repetition Penalty
↺
1
2
Web Search Settings
Max Results
Max Chars/Result
Search Timeout (s)
↺
0
30
Clear Chat
Cancel Generation
Chatbot
Textbox