models: - model: deepseek-ai/deepseek-math-7b-rl # No parameters necessary for base model - model: deepseek-ai/deepseek-math-7b-instruct parameters: density: 0.66 weight: 0.2 - model: deepseek-ai/deepseek-math-7b-base parameters: density: 0.57 weight: 0.2 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.54 weight: 0.1 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.61 weight: 0.1 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.65 weight: 0.1 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.55 weight: 0.1 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.55 weight: 0.1 - model: deepseek-ai/deepseek-math-7b-rl parameters: density: 0.55 weight: 0.1 merge_method: dare_ties base_model: deepseek-ai/deepseek-math-7b-rl dtype: bfloat16 experts_per_token: 3