This model was produced by first merging Qwen/Qwen3-8B-Base with Qwen/Qwen3-8B, OpenDataArena/Qwen3-8B-ODA-Math-460k, mlabonne/Qwen3-8B-abliterated using the DELLA MergeKit method (della). AIM was then applied to that merged parent using calibration examples from allenai/WildChat.
