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 TIES MergeKit method (ties). AIM was then applied to that merged parent using calibration examples from allenai/WildChat.
Downloads last month
8
Safetensors
Model size
8B params
Tensor type
BF16
ยท
Model tree for libvm/mm-cand-aim_on_ties__calib_instruction