models: - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B - model: qihoo360/Light-R1-14B-DS - model: Qwen/Qwen2.5-14B - model: Qwen/Qwen2.5-14B-Instruct - model: rombodawg/Rombos-Coder-V2.5-Qwen-14b - model: arcee-ai/Virtuoso-Small - model: tanliboy/lambda-qwen2.5-14b-dpo-test merge_method: model_stock base_model: Qwen/Qwen2.5-14B-Instruct tokenizer_source: base normalize: true int8_mask: true dtype: bfloat16