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

Code Llama, a state-of-the-art large language model for coding

ai.meta.com

Post reply on HN
Print view View original

51–60 of 525 posts

Re: Code Llama, a state-of-the-art large language model for coding

#51

Post by benvolio »

>The Code Llama models provide stable generations with up to 100,000 tokens of context.

Not a bad context window, but makes me wonder how embedded code models would pick that context when dealing with a codebase larger than 100K tokens.

And this makes me further wonder if, when coding with such a tool (or at least a knowledge that they’re becoming more widely used and leaned on), are there some new considerations that we should be applying (or at least starting to think about) when programming? Perhaps having more or fewer comments, perhaps more terse and less readable code that would consume fewer tokens, perhaps different file structures, or even more deliberate naming conventions (like Hungarian notation but for code models) to facilitate searching or token pattern matching of some kind. Ultimately, in what ways could (or should) we adapt to make the most of these tools?

Re: Code Llama, a state-of-the-art large language model for coding

#52

Post by brucethemoose2 »

naillo wrote: post #47

Feels like we're like a year away from local LLMs that can debug code reliably (via being hooked into console error output as well) which will be quite the exciting day.

That sounds like an interesting finetuning dataset.

Imagine a database of "Here is the console error, here is the fix in the code"

Maybe one could scrape git issues with console output and tagged commits.

Re: Code Llama, a state-of-the-art large language model for coding

#55

Post by Eddygandr »

coder543 wrote: post #26
ramesh31 wrote: post #24

Earlier quoted context omitted.

>Even the 7B model of code llama seems to be competitive with Codex, the model behind copilot It's extremely good. I keep a terminal tab open with 7b running for all of my "how do I do this random thing" questions while coding. It's pretty much replaced Google/SO for me.

You've already downloaded and thoroughly tested the 7B parameter model of "code llama"? I'm skeptical.

Maybe confused Code Llama with Llama 2?

Re: Code Llama, a state-of-the-art large language model for coding

#57

Post by tyre »

coder543 wrote: post #46
realce wrote: post #44

Earlier quoted context omitted.

Just sign up at meta and you'll get an email link in like 5 minutes

Yes, that's not a response to my comment. No one who has been using any model for just the past 30 minutes would say that it has "pretty much replaced Google/SO" for them, unless they were being facetious.

They said 7b llama which I read as the base LLaMa model, not this one specifically. All of these LLMs are trained on Stack Overflow so it makes sense that they’d be good out of the box.

Re: Code Llama, a state-of-the-art large language model for coding

#58

Post by darrenf »

titaniumtown wrote: post #29
jspisak wrote: post #10

Earlier quoted context omitted.

If you watch the Connect talks, I'll be speaking about this..

what is that?

Facebook Connect is what used to be called Oculus Connect. Kinda their equivalent of Apple's WWDC, I guess. It's when and where the Quest 3 will be officially unveiled in full, for example.

Re: Code Llama, a state-of-the-art large language model for coding

#59

Post by brucethemoose2 »

benvolio wrote: post #51

>The Code Llama models provide stable generations with up to 100,000 tokens of context. Not a bad context window, but makes me wonder how embedded code models would pick that context when dealing with a codebase larger than 100K tokens. And this makes me further wonder if, when coding with such a tool (or at least a knowledge that they’re becoming more widely used and leaned on), are there some new considerations tha…

This sounds like a job for middleware. Condensing split code into a single huge file, shortening comments, removing whitespace and such can be done by a preprocessor for the llm.

Re: Code Llama, a state-of-the-art large language model for coding

#60

Post by Eddygandr »

jspisak wrote: post #14
msoad wrote: post #5

Is there any place we can try those models? Are they available on HuggingFace?

Partner integrations will follow. For now we just have the weights available. But don't worry, this community moves fast!

Probably superseded (by y’all) within a week!
Post reply on HN