Vortex Reasoning Collection Experimental model to mimic GRPO but using SFT β’ 2 items β’ Updated Apr 27, 2025
Reasoning Collection Reasoning models which uses thinking tokens like Deepseek R1 β’ 2 items β’ Updated Apr 27, 2025
Vortex Collection SFT Models which is tuned on high quality dataset β’ 2 items β’ Updated Apr 27, 2025