{ "measurement": { "model.layers.0": { "accuracy": 0.9535447359085083, "total_bits": 296346912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.1": { "accuracy": 0.9570767879486084, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.2": { "accuracy": 0.9590513706207275, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.3": { "accuracy": 0.9570000171661377, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.4": { "accuracy": 0.9529976844787598, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.5": { "accuracy": 0.9522297382354736, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.6": { "accuracy": 0.9527850151062012, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.7": { "accuracy": 0.967296838760376, "total_bits": 308013792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.8": { "accuracy": 0.9617153406143188, "total_bits": 296346912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.9": { "accuracy": 0.9558558464050293, "total_bits": 296346912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.10": { "accuracy": 0.961064338684082, "total_bits": 308013792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.11": { "accuracy": 0.9479024410247803, "total_bits": 319680672, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.12": { "accuracy": 0.9536442756652832, "total_bits": 198380032, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.13": { "accuracy": 0.9531874656677246, "total_bits": 198380032, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.14": { "accuracy": 0.9519779682159424, "total_bits": 198380032, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.15": { "accuracy": 0.9532725811004639, "total_bits": 198380032, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.16": { "accuracy": 0.956120491027832, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.17": { "accuracy": 0.9555456638336182, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.18": { "accuracy": 0.9539203643798828, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.19": { "accuracy": 0.9534120559692383, "total_bits": 244989792, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.20": { "accuracy": 0.9578115940093994, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.21": { "accuracy": 0.9579923152923584, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.22": { "accuracy": 0.9582035541534424, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.23": { "accuracy": 0.9552838802337646, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.24": { "accuracy": 0.9604921340942383, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.25": { "accuracy": 0.9500429630279541, "total_bits": 319680672, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.26": { "accuracy": 0.9604992866516113, "total_bits": 190155456, "o_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.27": { "accuracy": 0.9601393938064575, "total_bits": 181780736, "o_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.28": { "accuracy": 0.9593974351882935, "total_bits": 181780736, "o_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.29": { "accuracy": 0.9595791101455688, "total_bits": 181780736, "o_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.30": { "accuracy": 0.9596754312515259, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.31": { "accuracy": 0.959135890007019, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.32": { "accuracy": 0.9589416980743408, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.33": { "accuracy": 0.9597592353820801, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.34": { "accuracy": 0.95875084400177, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.35": { "accuracy": 0.9580636024475098, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.36": { "accuracy": 0.9574229717254639, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.37": { "accuracy": 0.9579139947891235, "total_bits": 181780736, "o_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "2": 8 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.38": { "accuracy": 0.959316611289978, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.39": { "accuracy": 0.9586589336395264, "total_bits": 264834912, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "q_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "k_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "v_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 16 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } } } }