{ "measurement": { "model.layers.0": { "accuracy": 0.7494020462036133, "total_bits": 120876576, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.1": { "accuracy": 0.8237600326538086, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.2": { "accuracy": 0.8662686347961426, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.3": { "accuracy": 0.8621411323547363, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.4": { "accuracy": 0.856804370880127, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.5": { "accuracy": 0.8192110061645508, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.6": { "accuracy": 0.7364501953125, "total_bits": 120876576, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.7": { "accuracy": 0.9165894985198975, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.8": { "accuracy": 0.9087321758270264, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.9": { "accuracy": 0.9050393104553223, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.10": { "accuracy": 0.90169358253479, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.11": { "accuracy": 0.9000589847564697, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.12": { "accuracy": 0.888805627822876, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.13": { "accuracy": 0.8871350288391113, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.14": { "accuracy": 0.8753108978271484, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.15": { "accuracy": 0.8793735504150391, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.16": { "accuracy": 0.8758792877197266, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.17": { "accuracy": 0.8746852874755859, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.18": { "accuracy": 0.8734469413757324, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.19": { "accuracy": 0.8737640380859375, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.20": { "accuracy": 0.886871337890625, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.21": { "accuracy": 0.88153076171875, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.22": { "accuracy": 0.8707356452941895, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.23": { "accuracy": 0.8127593994140625, "total_bits": 112619808, "q_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "o_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } } } }