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

The Illustrated Transformer

jalammar.github.io

Post reply on HN
Print view View original

51–60 of 92 posts

Re: The Illustrated Transformer

#51

Post by brcmthrowaway »

libraryofbabel wrote: post #48
brcmthrowaway wrote: post #45

Earlier quoted context omitted.

How was reinforcement learning used as a gamechanger? What happens to an LLM without reinforcement learning?

The essence of it is that after the "read the whole internet and predict the next token" pre-training step (and the chat fine-tuning), SotA LLMs now have a training step where they solve huge numbers of tasks that have verifiable answers (especially programming and math). The model therefore gets the very broad general knowledge and natural language abilities from pre-training and gets good at solving actual problems…

Do you have the answer to the second question? Is an LLM trained on the internet just GPT-3?

Re: The Illustrated Transformer

#52

Post by libraryofbabel »

brcmthrowaway wrote: post #51
libraryofbabel wrote: post #48

Earlier quoted context omitted.

The essence of it is that after the "read the whole internet and predict the next token" pre-training step (and the chat fine-tuning), SotA LLMs now have a training step where they solve huge numbers of tasks that have verifiable answers (especially programming and math). The model therefore gets the very broad general knowledge and natural language abilities from pre-training and gets good at solving actual problems…

Do you have the answer to the second question? Is an LLM trained on the internet just GPT-3?

I don't know - perhaps someone who's more of an expert or who's worked a lot with open source models that haven't been RL-ed can weigh in here!

But certainly without the RL step, the LLM would be much worse at coding and would hallucinate more.

Re: The Illustrated Transformer

#53

Post by malaya_zemlya »

brcmthrowaway wrote: post #45
libraryofbabel wrote: post #30

I read this article back when I was learning the basics of transformers; the visualizations were really helpful. Although in retrospect knowing how a transformer works wasn't very useful at all in my day job applying LLMs, except as a sort of deep background for reassurance that I had some idea of how the big black box producing the tokens was put together, and to give me the mathematical basis for things like contex…

How was reinforcement learning used as a gamechanger? What happens to an LLM without reinforcement learning?

You can download a base model (aka foundation, aka pretrain-only) from huggingface and test it out. These were produced without any RL.

However, most modern LLMs, even base models, would be not just trained on raw internet text. Most of them were also fed a huge amount of synthetic data. You often can see the exact details in their model cards. As a result, if you sample from them, you will notice that they love to output text that looks like:

  6. **You will win millions playing bingo.**
     - **Sentiment Classification: Positive**
     - **Reasoning:** This statement is positive as it suggests a highly favorable outcome for the person playing bingo.
This is not your typical internet page.

Re: The Illustrated Transformer

#54

Post by sifar »

krackers wrote: post #50
throw310822 wrote: post #20

Earlier quoted context omitted.

I might be completely off road, but I can't help thinking of convolutions as my mental model for the K Q V mechanism. Attention has the same property of a convolution kernel of being trained independently of position; it learns how to translate a large, rolling portion of an input to a new "digested" value; and you can train multiple ones in parallel so that they learn to focus on different aspects of the input ("ker…

I think there are two key differences though: 1) Attention doesn't doesn't use fixed distance-dependent weight for the aggregation but instead the weight becomes "semantically-dependent", based on association between q/k. 2) A single convolution step is a local operation (only pulling from nearby pixels), whereas attention is a "global" operation, pulling from the hidden states of all previous tokens. (Maybe sliding…

Nested concolutikns, dilated convolutiona both can pull in data from further afar.

Re: The Illustrated Transformer

#55

Post by tayo42 »

D-Machine wrote: post #9
red2awn wrote: post #3

Earlier quoted context omitted.

Implement transformers yourself (ie in Numpy). You'll never truly understand it by just watching videos.

Seconding this, the terms "Query" and "Value" are largely arbitrary and meaningless in practice, look at how to implement this in PyTorch and you'll see these are just weight matrices that implement a projection of sorts, and self-attention is always just self_attention(x, x, x) or self_attention(x, x, y) in some cases, where x and y are are outputs from previous layers. Plus with different forms of attention, e.g. m…

>the terms "Query" and "Value" are largely arbitrary and meaningless in practice

This is the most confusing thing about it imo. Those words all mean something but they're just more matrix multiplications. Nothing was being searched for.

Re: The Illustrated Transformer

#56

Post by octoberfranklin »

malaya_zemlya wrote: post #53
brcmthrowaway wrote: post #45

Earlier quoted context omitted.

How was reinforcement learning used as a gamechanger? What happens to an LLM without reinforcement learning?

You can download a base model (aka foundation, aka pretrain-only) from huggingface and test it out. These were produced without any RL. However, most modern LLMs, even base models, would be not just trained on raw internet text. Most of them were also fed a huge amount of synthetic data. You often can see the exact details in their model cards. As a result, if you sample from them, you will notice that they love to o…

You often can see the exact details in their model cards.

Bwahahahaaha. Lol.

/me falls off of chair laughing

Come on, I've never found "exact details" about anything in a model card, except maybe the number of weights.

Re: The Illustrated Transformer

#57

Post by holtkam2 »

libraryofbabel wrote: post #30

I read this article back when I was learning the basics of transformers; the visualizations were really helpful. Although in retrospect knowing how a transformer works wasn't very useful at all in my day job applying LLMs, except as a sort of deep background for reassurance that I had some idea of how the big black box producing the tokens was put together, and to give me the mathematical basis for things like contex…

I agree and disagree. In my day job as an AI engineer I rarely if ever need to use any “classic” deep learning to get things done. However, I’m a firm believer that understanding the internals of a LLM can set you apart as an gen AI engineer, if you’re interested in becoming the top 1% in your field. There can and will be situations where your intuition about the constraints of your model is superior compared to peers who consider the LLM a black box. I had this advice given directly to me years ago, in person, by Clem Delangue of Hugging Face - I took it seriously and really doubled down on understanding the guts of LLMs. I think it’s served me well.

I’d give similar advice to any coding bootcamp grad: yes you can get far by just knowing python and React, but to reach the absolute peak of your potential and join the ranks of the very best in the world in your field, you’ll eventually want to dive deep into computer architecture and lower level languages. Knowing these deeply will help you apply your higher level code more effectively than your coding bootcamp classmates over the course of a career.

Re: The Illustrated Transformer

#58

Post by energy123 »

libraryofbabel wrote: post #30

I read this article back when I was learning the basics of transformers; the visualizations were really helpful. Although in retrospect knowing how a transformer works wasn't very useful at all in my day job applying LLMs, except as a sort of deep background for reassurance that I had some idea of how the big black box producing the tokens was put together, and to give me the mathematical basis for things like contex…

An example of why a basic understanding is helpful:

A common sentiment on HN is that LLMs generate too many comments in code.

But comment spam is going to help code quality, due to the way causal transformers and positional encoding works. The model has learned to dump locally-specific reasoning tokens where they're needed, in a tightly scoped cluster that can be attended to easily, and forgetting about just as easily later on. It's like a disposable scratchpad to reduce the errors in the code it's about to write.

The solution to comment spam is textual/AST post-processing of generated code, rather than prompting the LLM to handicap itself by not generating as much comments.

Re: The Illustrated Transformer

#59

Post by D-Machine »

profsummergig wrote: post #10
D-Machine wrote: post #9

Earlier quoted context omitted.

Seconding this, the terms "Query" and "Value" are largely arbitrary and meaningless in practice, look at how to implement this in PyTorch and you'll see these are just weight matrices that implement a projection of sorts, and self-attention is always just self_attention(x, x, x) or self_attention(x, x, y) in some cases, where x and y are are outputs from previous layers. Plus with different forms of attention, e.g. m…

Do you think the dimension reduction is necessary? Or is it just practical (due to current hardware scarcity)?

Definitely mostly just a practical thing IMO, especially with modern attention variants (sparse attention, FlashAttention, linear attention, merged attention etc). Not sure it is even hardware scarcity per se / solely, it would just be really expensive in terms of both memory and FLOPs (and not clearly increase model capacity) to use larger matrices.

Also for the specific part where you, in code for encoder-decoder transformers, call the a(x, x, y) function instead of the usual a(x, x, x) attention call (what Alammar calls "encoder-decoder attention" in his diagram just before the "The Decoder Side"), you have different matrix sizes, so dimension reduction is needed to make the matrix multiplications work out nicely too.

But in general it is just a compute thing IMO.

Re: The Illustrated Transformer

#60

Post by D-Machine »

tayo42 wrote: post #55
D-Machine wrote: post #9

Earlier quoted context omitted.

Seconding this, the terms "Query" and "Value" are largely arbitrary and meaningless in practice, look at how to implement this in PyTorch and you'll see these are just weight matrices that implement a projection of sorts, and self-attention is always just self_attention(x, x, x) or self_attention(x, x, y) in some cases, where x and y are are outputs from previous layers. Plus with different forms of attention, e.g. m…

>the terms "Query" and "Value" are largely arbitrary and meaningless in practice This is the most confusing thing about it imo. Those words all mean something but they're just more matrix multiplications. Nothing was being searched for.

Better resources will note the terms are just historical and not really relevant anymore, and just remain a naming convention for self-attention formulas. IMO it is harmful to learning and good pedagogy to say they are anything more than this, especially as we better understand the real thing they are doing is approximating feature-feature correlations / similarity matrices, or perhaps even more generally, just allow for multiplicative interactions (https://openreview.net/forum?id=rylnK6VtDH).
Post reply on HN