{ "measurement": { "model.layers.0": { "accuracy": 0.6285324096679688, "total_bits": 289320576, "o_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 }, "qkv_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.1": { "accuracy": 0.695317268371582, "total_bits": 289320576, "o_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 }, "qkv_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.2": { "accuracy": 0.6292324066162109, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.3": { "accuracy": 0.5984973907470703, "total_bits": 252161664, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.4": { "accuracy": 0.6389684677124023, "total_bits": 252161664, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.5": { "accuracy": 0.7461767196655273, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.6": { "accuracy": 0.7727584838867188, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.7": { "accuracy": 0.798675537109375, "total_bits": 252161664, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.8": { "accuracy": 0.8624000549316406, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.9": { "accuracy": 0.8816728591918945, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.10": { "accuracy": 0.8820247650146484, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.11": { "accuracy": 0.8820934295654297, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.12": { "accuracy": 0.878394603729248, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.13": { "accuracy": 0.7176222801208496, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.14": { "accuracy": 0.932328462600708, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.15": { "accuracy": 0.9327261447906494, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.16": { "accuracy": 0.9302468299865723, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.17": { "accuracy": 0.926159143447876, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.18": { "accuracy": 0.9201779365539551, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.19": { "accuracy": 0.9235491752624512, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.20": { "accuracy": 0.9098367691040039, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.21": { "accuracy": 0.909736156463623, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.22": { "accuracy": 0.9064040184020996, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.23": { "accuracy": 0.9041399955749512, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.24": { "accuracy": 0.896183967590332, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.25": { "accuracy": 0.8960213661193848, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.26": { "accuracy": 0.8992471694946289, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.27": { "accuracy": 0.8962163925170898, "total_bits": 233583360, "o_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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.28": { "accuracy": 0.8950643539428711, "total_bits": 252161664, "o_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "down_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.29": { "accuracy": 0.874481201171875, "total_bits": 301703808, "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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.30": { "accuracy": 0.9012396335601807, "total_bits": 301703808, "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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 } }, "model.layers.31": { "accuracy": 0.9370012283325195, "total_bits": 400793088, "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 }, "qkv_proj": { "group_size": { "2": 64 }, "bits": [ 2 ], "bits_prop": [ 1 ], "scale_bits": 4 }, "gate_up_proj": { "group_size": { "4": 128 }, "bits": [ 4 ], "bits_prop": [ 1 ], "scale_bits": 4 } } } }