slices: - sources: - model: ClaudioItaly/Underground layer_range: [0, 2] parameters: attention: - filter: o_proj value: 1.15 - filter: q_proj value: 1.15 - filter: v_proj value: 1.1 - filter: down_proj value: 1.0 - sources: - model: ClaudioItaly/Underground layer_range: [2, 6] parameters: attention: - filter: o_proj value: 1.3 - filter: q_proj value: 1.25 - filter: v_proj value: 1.2 - filter: down_proj value: 1.15 - sources: - model: ClaudioItaly/Underground layer_range: [6, 12] parameters: attention: - filter: o_proj value: 1.5 - filter: q_proj value: 1.4 - filter: v_proj value: 1.35 - filter: down_proj value: 1.3 - sources: - model: ClaudioItaly/Underground layer_range: [12, 20] parameters: attention: - filter: o_proj value: 1.75 - filter: q_proj value: 1.6 - filter: v_proj value: 1.5 - filter: down_proj value: 1.4 - sources: - model: ClaudioItaly/Underground layer_range: [20, 28] parameters: attention: - filter: o_proj value: 2.0 - filter: q_proj value: 1.85 - filter: v_proj value: 1.75 - filter: down_proj value: 1.6 - sources: - model: ClaudioItaly/Underground layer_range: [28, 36] parameters: attention: - filter: o_proj value: 2.2 - filter: q_proj value: 2.0 - filter: v_proj value: 1.9 - filter: down_proj value: 1.8 - sources: - model: ClaudioItaly/Underground layer_range: [36, 42] parameters: attention: - filter: o_proj value: 2.5 - filter: q_proj value: 2.3 - filter: v_proj value: 2.2 - filter: down_proj value: 2.0 - sources: - model: ClaudioItaly/Underground layer_range: [42, 48] parameters: attention: - filter: o_proj value: 3.0 - filter: q_proj value: 2.7 - filter: v_proj value: 2.5 - filter: down_proj value: 2.3 merge_method: passthrough dtype: bfloat16