Re:An analysis of DeepSeek's R1-Zero and R1
by visarga on Thursday January 30, 2025 @12:19AM
(#42875130)
> I wonder if there is a cap to multi head attention architecture
I don't think there is a cap other than having good data. The model learns all languages in the world, it has capacity. A simple model like AlphaZero beats humans at board games. As long as you have data, the model is not an obstacle. A LLM like AlphaProof is ranked silver medal at IMO.
I don't think there is a cap other than having good data. The model learns all languages in the world, it has capacity. A simple model like AlphaZero beats humans at board games. As long as you have data, the model is not an obstacle. A LLM like AlphaProof is ranked silver medal at IMO.