Re:Training LLMs to Reason in a Continuous Latent Space
by cootsnuck on Wednesday December 11, 2024 @09:05AM
(#42387785)
So perhaps could be useful for fine-tuning on smaller models?
[ Parent
| on HN ]
Re:Training LLMs to Reason in a Continuous Latent Space
by max93 on Wednesday December 11, 2024 @11:04AM
(#42389139)
I think so. I believe this type of reasoning method, which achieves better results through longer computation time, is very useful on edge devices like mobile phones. Consider a scenario where we only need the model to output a function/action call on the phone; we don't require it to provide an immediate response.