Open Source LLM Chat

This app uses Qwen/Qwen2.5-1.5B-Instruct - an open-source language model.

Features:

  • Interactive chat interface
  • Adjustable generation parameters
  • Custom system messages
  • Deployed on Hugging Face Spaces

Settings

50 2048
0.1 2
0.1 1

Parameter Guide:

  • Max Tokens: Maximum length of response
  • Temperature: Higher = more creative, Lower = more focused
  • Top-p: Controls diversity of word choices

Tips:

  • Start with a clear, specific question
  • Adjust temperature for creative vs. factual responses
  • Use system messages to set the AI's behavior
  • Clear chat if responses become inconsistent