I don't think this is optimized, but I'm getting about an average of 715Mh/s on for my 2 7970s @ 1180/110 with this config:
"intensity" : "8,8",
"vectors" : "1,1",
"worksize" : "64,64",
"kernel" : "poclbm,poclbm",
"api-port" : "4028",
"expiry" : "120",
"gpu-dyninterval" : "8",
"gpu-platform" : "0",
"gpu-threads" : "2",
"log" : "5",
"no-pool-disable" : true,
"no-submit-stale" : true,
"queue" : "2",
"scan-time" : "20",
"shares" : "0",
"kernel-path" : "/usr/local/bin"