OptiLLM - Optimizing LLM Inference
System message
Max new tokens
↺
1
4096
Temperature
↺
0.1
4
Top-p (nucleus sampling)
↺
0.1
1
Chat
Compare
Chat
Compare
Model
Approach
Chatbot
Textbox
Submit
Clear
Model
Approach
Model
Approach
Enter your message for comparison
Compare
Response 1
Response 2