Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "code transformers"
-
Just go to GPT and get me the code today!!!
Like wtf why does every non-tech guy thinks GPT is the solution for each problem.
So, a workmate wanted a fullstack system ready in 2 days and argues that its too easy with GPT. I mean yeah GPT helps, sometimes, on frequent rare occasions. But, that can't be the solution to everything, like ask it to setup the whole backend frontend integration, will it? ask it to manage assets will it? ask it to write complex code, it fails, miserably, okay like me but that's the point. Just because random transformers pop up each week containing some random shitty weights (not always agreed) that can't replace a full stack developer. These 'attention' seeking models are as good as another tool, a bit efficient, but at the end of the day its just a tool, all it does is lessen the typing time but gives more errors too. The average time remains the same. And my non-tech manager can't understand he can't do it himself earlier using GPT. Succkkkkkkssss!5 -
After a lot of work I figured out how to build the graph component of my LLM. Figured out the basic architecture, how to connect it in, and how to train it. The design and how-to is 100%.
Ironically generating the embeddings is slower than I expect the training itself to take.
A few extensions of the design will also allow bootstrapped and transfer learning, and as a reach, unsupervised learning but I still need to work out the fine details on that.
Right now because of the design of the embeddings (different from standard transformers in a key aspect), they're slow. Like 10 tokens per minute on an i5 (python, no multithreading, no optimization at all, no training on gpu). I've came up with a modification that takes the token embeddings and turns them into hash keys, which should be significantly faster for a variety of reasons. Essentially I generate a tree of all weights, where the parent nodes are the mean of their immediate child nodes, split the tree on lesser-than-greater-than values, and then convert the node values to keys in a hashmap to make lookup very fast.
Weight comparison can be done either directly through tree traversal, or using normalized hamming distance between parent/child weight keys and the lookup weight.
That last bit is designed already and just needs implemented but it is completely doable.
The design itself is 100% attention free incidentally.
I'm outlining the step by step, only the essentials to train a word boundary detector, noun detector, verb detector, as I already considered prior. But now I'm actually able to implement it.
The hard part was figuring out the *graph* part of the model, not the NN part (if you could even call it an NN, which it doesn't fit the definition of, but I don't know what else to call it). Determining what the design would look like, the necessary graph token types, what function they should have, *how* they use the context, how thats calculated, how loss is to be calculated, and how to train it.
I'm happy to report all that is now settled.
I'm hoping to get more work done on it on my day off, but thats seven days away, 9-10 hour shifts, working fucking BurgerKing and all I want to do is program.
And all because no one takes me seriously due to not having a degree.
Fucking aye. What is life.
If I had a laptop and insurance and taxes weren't a thing, I'd go live in my car and code in a fucking mcdonalds or a park all day and not have to give a shit about any of these other externalities like earning minimum wage to pay 25% of it in rent a month and 20% in taxes and other government bullshit.4 -
I want to build a code transpiler/ transformer as a side project I looked around but I can't find where to start.
Does anyone have any useful info on this ?1