models: - model: allura-org/GLM4-9B-Neon-v2 - model: THUDM/LongReward-glm4-9b-DPO parameters: weight: [0.496, 0.166, 0.166, 0.496, 0.496, 0.166, 0.166, 0.496] base_model: allura-org/GLM4-9B-Neon-v2 merge_method: sce parameters: select_topk: 0.06 lambda: 0.66 tokenizer_source: base dtype: float32 out_dtype: bfloat16