[TekMol]

Great, thanks for the clarification.

And how does the NN represent the token at the output layer? Is it a binary representation of the token number?

Or does it have a neuron for each token it knows and ChatGPT takes the most activated neuron as the answer?

[mirekrusin]

Tokens are integers that map to text tokens.

Tokens are part of words, approx 4 characters or 75% of word.

It gives a list of tokens with their probabilities on output.

It's a short list with highest probabilities.

Temperature controls which tokens to pick - usually 0% = top one only (consistent results), closer to 100% means more randomness (more "creativity").

[joshspankit]

Since we’re here: Does a “resused” token count as a second token?

For example: if you limited all inout/output to the same 100 words, could you stay within the token limit permanently?

[vorticalbox]

so a glorified Markov chain?

[TeMPOraL]

Yes, in the same sense a modern digital camera is a glorified photodiode. In both cases, light comes in, voltage comes out, and we can use it to count how much light came in.

[mirekrusin]

Why stop there, it's just ones and zeroes.

It's "glorified markov chain" in the same sense that sqlite is just "glorified bubble sort".

[visarga]

Don't you know that "attention is all you need"? Attention is non-markovian. It's all-to-all with some masking, not a chain.

[zwaps]

Basically the latter

[weinzierl]

The tokenization algorithms I encountered all had around 50000 tokens, which fits nicely into (and makes good use of) a 16-bit number. Is this just a coincidence or does it have advantages for the token to be a 16-bit representable number?

[danuker]

I suspect it being 16 bit instead of 32 bit means more of them can get packed more tightly. Some instructions can operate on them in parallel.

But I personally think it's a coincidence, and it just so happens that 50k tokens are enough for the level of complexity the models have right now.

[sebzim4500]

Probably a coincidence. The GPT-4 and GPT-3.5 tokenizer has 100k tokens.