models: - model: TareksLab/M-MERGE4 parameters: weight: - filter: self_attn value: [0.3, 0.1, 0.2] - filter: mlp value: [0.4, 0.2, 0.1] - value: 0.2 density: 0.7 lambda: 1.05 - model: TareksLab/M-MERGE3 parameters: weight: - filter: self_attn value: [0.2, 0.1, 0.3] - filter: mlp value: [0.3, 0.1, 0.2] - value: 0.2 density: 0.65 lambda: 1.05 - model: TareksLab/M-MERGE2 parameters: weight: - filter: self_attn value: [0.1, 0.3, 0.1] - filter: mlp value: [0.2, 0.3, 0.1] - value: 0.2 density: 0.6 lambda: 1.05 - model: TareksLab/M-MERGE1 parameters: weight: - filter: self_attn value: [0.2, 0.2, 0.1] - filter: mlp value: [0.1, 0.2, 0.2] - value: 0.2 density: 0.6 lambda: 1 - model: TareksLab/M-BASE-SCE parameters: weight: - filter: self_attn value: [0.1, 0.3, 0.3] - filter: mlp value: [0.1, 0.2, 0.4] - value: 0.2 density: 0.55 lambda: 1 base_model: TareksLab/M-BASE-SCE merge_method: dare_ties parameters: normalize: false pad_to_multiple_of: 4 tokenizer: source: TareksLab/M-TOKENIZER-SCE chat_template: llama3 dtype: bfloat16