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 open-web-math/open-web-math.
- Downloads last month
- 18
Model tree for libvm/mm-cand-aim_on_della__calib_reasoning
Base model
Qwen/Qwen3-8B-Base Finetuned
OpenDataArena/Qwen3-8B-ODA-Math-460k