# this makes use of llama-swap's profile feature to
# keep the architect and editor models in VRAM on different GPUs

- name: "openai/aider:QwQ"
  edit_format: diff
  extra_params:
    max_tokens: 16384
    top_p: 0.95
    top_k: 40
    presence_penalty: 0.1
    repetition_penalty: 1
    num_ctx: 16384
  use_temperature: 0.6
  reasoning_tag: think
  weak_model_name: "openai/aider:qwen-coder-32B"
  editor_model_name: "openai/aider:qwen-coder-32B"

- name: "openai/aider:qwen-coder-32B"
  edit_format: diff
  extra_params:
    max_tokens: 16384
    top_p: 0.8
    top_k: 20
    repetition_penalty: 1.05
  use_temperature: 0.6
  reasoning_tag: think
  editor_edit_format: editor-diff
  editor_model_name: "openai/aider:qwen-coder-32B"