What determines how many vectors can be fed into the EncoderLayer? In the next video your prompt embeds as 3 vectors, but could have easily been more (in a different dictionary). I don't see that number in any of the parameters here... Thank you for the excellent videos, btw!
Amazing!! Waiting for more videos :)
What determines how many vectors can be fed into the EncoderLayer? In the next video your prompt embeds as 3 vectors, but could have easily been more (in a different dictionary). I don't see that number in any of the parameters here... Thank you for the excellent videos, btw!
thank you
Can you explain sparse attention? please please