Comment by irthomasthomas
21 hours ago
Given that 4.7 was a brand new model, trained from scratch with a unique architecture and tokenization scheme, I don't see the same pattern. It seems arbitrary.
21 hours ago
Given that 4.7 was a brand new model, trained from scratch with a unique architecture and tokenization scheme, I don't see the same pattern. It seems arbitrary.
i dont understand the nuances here. what does this mean. 4.8 is trained on same model as previous one then? what does brand new mean.
It means for 4.7 they trained a new base model with different architecture, different pre-training data (later knowledge cutoff), and a new tokenizer. Vs finetuning an existing model, which was the case for 4.6, and probably for 4.8.
do you mean pre training? so 4.8 is just post training of an old pretrained model?
btw where do they tell you how they trained the model.