SenseTime open-sources SenseNova-Loop-9B-Preview, a multimodal model that runs its middle layers twice
Released Oct 30 under Apache 2.0, the ~9B text-and-image model reuses a block of 24 decoder layers twice with shared weights, giving about 14.6B parameters' worth of compute per pass, with 262K-token training context aimed at long-context coding and tool-use agents. It's a preview: loading needs trust_remote_code=True (about 38 GB of BF16 weights) and there's no technical report yet, so treat its benchmark chart as unverified (GitHub).