base_model: Qwen/Qwen2-1.5B
architecture: qwen
experts:
  - source_model: Qwen/Qwen2-1.5B
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
    - "I want"
  - source_model: Replete-AI/Replete-Coder-Qwen2-1.5b
    positive_prompts:
    - "code"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
shared_experts:
  - source_model: Qwen/Qwen2-1.5B
    positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed
      - "chat"
    # (optional, but recommended:)
    residual_scale: 0.1 # downweight output from shared expert to prevent overcooking the model