{ "measurement": { "model.layers.0": { "accuracy": 0.9305233955383301, "total_bits": 47656992, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_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 } }, "model.layers.1": { "accuracy": 0.961686372756958, "total_bits": 51784992, "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 }, "o_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 }, "gate_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 } }, "model.layers.2": { "accuracy": 0.9639403820037842, "total_bits": 51784992, "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 }, "o_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 }, "gate_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 } }, "model.layers.3": { "accuracy": 0.9068508148193359, "total_bits": 41980320, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.4": { "accuracy": 0.9586918354034424, "total_bits": 49720992, "q_proj": { "group_size": { "2": 64 }, "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 }, "o_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 }, "gate_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 } }, "model.layers.5": { "accuracy": 0.9245643615722656, "total_bits": 34239648, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.6": { "accuracy": 0.9293514490127563, "total_bits": 30627648, "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": 0.9222983121871948, "total_bits": 30627648, "q_proj": { "group_size": { "2": 64 }, "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 }, "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": 0.9248720407485962, "total_bits": 30627648, "q_proj": { "group_size": { "2": 64 }, "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 }, "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": 0.9239978790283203, "total_bits": 28563648, "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": 0.9260375499725342, "total_bits": 30627648, "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.11": { "accuracy": 0.9440933465957642, "total_bits": 38367648, "q_proj": { "group_size": { "2": 64 }, "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 }, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.12": { "accuracy": 0.9411404132843018, "total_bits": 36303648, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.13": { "accuracy": 0.9282443523406982, "total_bits": 30627648, "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.14": { "accuracy": 0.9371697902679443, "total_bits": 36303648, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.15": { "accuracy": 0.9073450565338135, "total_bits": 30627648, "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.16": { "accuracy": 0.9269454479217529, "total_bits": 36303648, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.17": { "accuracy": 0.9374923706054688, "total_bits": 41980320, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.18": { "accuracy": 0.9396567344665527, "total_bits": 41980320, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.19": { "accuracy": 0.9197125434875488, "total_bits": 36303648, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.20": { "accuracy": 0.9247608184814453, "total_bits": 38367648, "q_proj": { "group_size": { "2": 64 }, "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 }, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.21": { "accuracy": 0.9209287166595459, "total_bits": 38367648, "q_proj": { "group_size": { "2": 64 }, "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 }, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.22": { "accuracy": 0.9368994235992432, "total_bits": 41980320, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.23": { "accuracy": 0.950645923614502, "total_bits": 47656992, "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": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_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 } } } }