A.X-K2
SK Telecom
SK Telecom's A.X K2 model, trained with Think-Fusion to support thinking and non-thinking responses in one checkpoint. The FP8 release uses sparse gated attention and 262,144-token context.
SK Telecom
SK Telecom's A.X K2 model, trained with Think-Fusion to support thinking and non-thinking responses in one checkpoint. The FP8 release uses sparse gated attention and 262,144-token context.