Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What are transformer models and how do they work?

txt.cohere.ai

Post reply on HN
Print view View original

41–50 of 114 posts

Re: What are transformer models and how do they work?

#41

Post by mdp2021 »

PeterisP wrote: post #40
riffraff wrote: post #28

Earlier quoted context omitted.

Was there any "big idea" after that? It seems most of the user-visible innovation has been "let's use transformers on more data". Perhaps capsule networks? But those are years old too.

No, not really, there was a lot of engineering work and bunch of not-so-big ideas (e.g. InstructGPT reinforcement learning after the model's training), but you can go from the transformers paper to current state of art without needing a "big idea". And I think this is the major "big idea", accepting the bitter lesson ( http://incompleteideas.net/IncIdeas/BitterLesson.html ) that major user-visible progress and new em…

I disagree. And first of all, there is a reflective meta teaching from the very idea of the "Bitter Lessons":

the past reveals that (in a way) "the application of models has not been a winner" - but we cannot really know that it is not, because we do not have obtained a model out of it, a model that shows why, an explanation - epistemologically, the "discouraging" protocols cannot be made a "law".

Practically, there still is a need to identify the proper architecture(s) to avoid the undesired weaknesses of the attempts in the current stages.

Re: What are transformer models and how do they work?

#42

Post by mirekrusin »

p-e-w wrote: post #24

The more I learn about the technical details of how ML systems are implemented, the more I feel that those details obscure , rather than illuminate, what is actually going on. It's as if we were trying to understand human ethics by looking at neurotransmitters or synapses in the brain. These structures seem way too low-level to actually explain the interesting stuff. What I hear is "something something transformer au…

It's not that difficult at the high level.

You give it input and have efficient way of amending weight to produce desired output.

You repeat this step for tons of examples.

At the end you end up with surprising behaviour where those amendments lead to emergent properties that generalize well.

Re: What are transformer models and how do they work?

#43

Post by p-e-w »

fruit2020 wrote: post #39
pmoriarty wrote: post #36

Earlier quoted context omitted.

This is called emergent behavior, and we don't know how it happens with organic brains, minds, and neurons either. It's actually pretty amazing that it's happening at all with computers, since neural nets are such simple, high level abstractions compared to how the brain works. It's possible that all the tremendous complexity of organic systems isn't actually necessary for intelligence or consciousnes, which is simil…

Do you mean that the gpt creators cannot backtrack an answer to understand how the model came up with it? If it’s such a black box how do they evolve it? Trial and error?

They can backtrack it of course, but the result is just billions of numbers – not any sort of "insight".

Re: What are transformer models and how do they work?

#44

Post by p-e-w »

pmoriarty wrote: post #36
p-e-w wrote: post #24

The more I learn about the technical details of how ML systems are implemented, the more I feel that those details obscure , rather than illuminate, what is actually going on. It's as if we were trying to understand human ethics by looking at neurotransmitters or synapses in the brain. These structures seem way too low-level to actually explain the interesting stuff. What I hear is "something something transformer au…

This is called emergent behavior, and we don't know how it happens with organic brains, minds, and neurons either. It's actually pretty amazing that it's happening at all with computers, since neural nets are such simple, high level abstractions compared to how the brain works. It's possible that all the tremendous complexity of organic systems isn't actually necessary for intelligence or consciousnes, which is simil…

> It's possible that all the tremendous complexity of organic systems isn't actually necessary for intelligence or consciousnes, which is similarly surprising.

My guess is most of that complexity is necessary for efficiency, not for basic function.

Biological systems are unimaginably efficient at almost everything they do. The information storage density of DNA is within 1-2 orders of magnitude of the upper limit imposed by physics, the brain performs tasks that you need GPU clusters to emulate while using only 20 Watts of energy, some catalytic enzymes are a million times better than a platinum catalyst, etc.

Re: What are transformer models and how do they work?

#45

Post by mdp2021 »

detrites wrote: post #37
antimora wrote: post #11

Earlier quoted context omitted.

I am trying to learn more in depth. Could you suggest some good resource for learning transformers?

This hour-long MIT lecture is very good, it builds from the ground up until transformers. MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention: https://youtube.com/watch?v=ySEx_Bqxvvo

The uploads of the 2023 MIT 6.S191 course from Alexander Amini (et alii) is ongoing, periodical since mid March. (They published the lesson about Reinforcement Learning yesterday.)

Re: What are transformer models and how do they work?

#46

Post by eiz »

jaidhyani wrote: post #5

Skimming it, there are a few things about this explanation that rub me just slightly the wrong way. 1. Calling the input token sequence a "command". It probably only makes sense to think of this as a "command" on a model that's been fine-tuned to treat it as such. 2. Skipping over BPE as part of tokenization - but almost every transformer explainer does this, I guess. 3. Describing transformers as using a "word embed…

> 4. Describing positional embeddings as multiplicative. They are generally (and very counterintuitively to me, but nevertheless) additive with token embeddings.

Worth noting that rotary position embeddings, used in many recent architectures (LLaMA, GPT-NeoX, ...), are very similar to the original sin/cos position embedding in the transformer paper but using complex multiplication instead of addition

Re: What are transformer models and how do they work?

#47

Post by iamflimflam1 »

fruit2020 wrote: post #39
pmoriarty wrote: post #36

Earlier quoted context omitted.

This is called emergent behavior, and we don't know how it happens with organic brains, minds, and neurons either. It's actually pretty amazing that it's happening at all with computers, since neural nets are such simple, high level abstractions compared to how the brain works. It's possible that all the tremendous complexity of organic systems isn't actually necessary for intelligence or consciousnes, which is simil…

Do you mean that the gpt creators cannot backtrack an answer to understand how the model came up with it? If it’s such a black box how do they evolve it? Trial and error?

Trial and error is pretty much what training is. You feed an input in and use the error to update the network.

What is surprising with these models is that the simple training leads to emergent behaviour that is much more powerful than what you’d expect from the training data.

With RHLF post training you can tweak these emergent behaviours by having a human (or a model trained to act like a human) give feedback on how good the output is.

So far I’ve not seen any good explanations for how this emergent behaviour happens or how it can be reverse engineered.

Re: What are transformer models and how do they work?

#48

Post by bomewish »

jaidhyani wrote: post #5

Skimming it, there are a few things about this explanation that rub me just slightly the wrong way. 1. Calling the input token sequence a "command". It probably only makes sense to think of this as a "command" on a model that's been fine-tuned to treat it as such. 2. Skipping over BPE as part of tokenization - but almost every transformer explainer does this, I guess. 3. Describing transformers as using a "word embed…

You seem to know a bunch about this. What’s your rec for best single explainer?

Re: What are transformer models and how do they work?

#50

Post by metanonsense »

antimora wrote: post #11
jaidhyani wrote: post #5

Skimming it, there are a few things about this explanation that rub me just slightly the wrong way. 1. Calling the input token sequence a "command". It probably only makes sense to think of this as a "command" on a model that's been fine-tuned to treat it as such. 2. Skipping over BPE as part of tokenization - but almost every transformer explainer does this, I guess. 3. Describing transformers as using a "word embed…

I am trying to learn more in depth. Could you suggest some good resource for learning transformers?

When I first tried to understand transformers, I superficially understood most material, but I always felt that I did not really get it on a "I am able to build it and I understand why I am doing it" level. I struggled to get my fingers on what exactly I did not understand. I read the original paper, blog posts, and watched more videos than I care to admit.

The one source of information that made it click to me were chapters 159 to 163 of Sebastian Raschka's phenomenal "Intro to deep learning and generative models" course on youtube. https://www.youtube.com/playlist?list=PLTKMiZHVd_2KJtIXOW0zF...

Post reply on HN