What are our LLMs actually trained on, and are we actually running out of data?
I think your link to 'Phi-1 by Microsoft' is not working!
Cool! May be relevant: https://arxiv.org/abs/2305.16264
I think your link to 'Phi-1 by Microsoft' is not working!
Cool! May be relevant: https://arxiv.org/abs/2305.16264