LLM Coding & Math Experiment

Query Qwen1.5-1.8B-Chat or Qwen Code models using ZeroGPU.

Select Model
32 2048
0.1 1.5
0.1 1

Notes:

  • Ensure you have accepted the terms of use for the selected Qwen models on the Hugging Face Hub.
  • Model loading can take some time, especially on the first run or when switching models.
  • This Space runs on ZeroGPU, which means GPU resources are allocated dynamically.