# Model configuration
model_path: ../utils/qwen3b_games
max_tokens: 1024
temperature: 0.6  # Lower temperature for more focused responses
top_p: 0.9  # From rollout top_p
developer_prompt: DeepSeekZero
developer_role: system  # Standard role for system prompts

# Output configuration
output_dir: results
save_metadata: true
save_full_results: true
eval_repeats: 3

# Categories and datasets to evaluate
categories:
  - category: reasoning
    datasets:
      - dataset: mahjong_puzzle
        size: 100
        seed: 42
        params:
          min_num_rounds: 10
          max_num_rounds:  50