News for hackers. Stuff that matters.
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by mensetmanusman on Thursday November 06, 2025 @10:18PM (#45843228)
Weights are meaningless without training data and source.
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by antiframe on Thursday November 06, 2025 @10:26PM (#45843274)
I get a lot of meaning out of weights and source (without the training data), not sure about you. Calling it meaningless seems like exaggeration.
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by mensetmanusman on Friday November 07, 2025 @09:53AM (#45847010)
Can you change the weights to improve?
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by HarHarVeryFunny on Friday November 07, 2025 @11:01AM (#45847763)
You can fine tune without the original training data, which for a large LLM is typically going to mean using LoRA - keeping the original weights unchanged and adding separate fine-tuning weights.
Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by danielmarkbruce on Monday November 10, 2025 @08:10PM (#45882964)
it's a bunch of numbers. Of course you can change them.