They even added a section ”AI Use Disclosure”, beautiful!
ramon156 15 hours ago [-]
Doesn't really explain why its faster. "Optimizing for every kind of CPU" is not really enough info.
Cool project nonetheless, I will go through the code later tomorrow
benj111 16 hours ago [-]
I kind of assumed the model would process the text 'directly', from what I understand, wouldn't this be biasing the input based on how you tokenise as it's lossy?
I assume this tradeoff is purely for speed/compression. Or am I missing what's going on here?
convexstrictly 16 hours ago [-]
Tokenization is done on the CPU. Models never see the raw characters. That's why you get trick questions like the number of r's in strawberry.
There are many research papers on models using characters directly. One challenge is that effective context length is smaller.
Cool project nonetheless, I will go through the code later tomorrow
I assume this tradeoff is purely for speed/compression. Or am I missing what's going on here?
There are many research papers on models using characters directly. One challenge is that effective context length is smaller.