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

251–260 of 525 posts

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

#251

Post by natrys »

Pesthuf wrote: post #239
mchiang wrote: post #223

Earlier quoted context omitted.

Ollama supports it already: `ollama run codellama:7b-instruct` https://ollama.ai/blog/run-code-llama-locally More models uploaded as we speak: https://ollama.ai/library/codellama

Isn't ollama terminal only? For code, that wouldn't be good.

They have a server/client model. The binary comes with a basic terminal front-end but you can just create your own self-hosted GUI or editor integration against the API[1]:

[1] https://github.com/jmorganca/ollama/blob/main/docs/api.md

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

#252

Post by gabereiser »

brucethemoose2 wrote: post #86
gabereiser wrote: post #74

Earlier quoted context omitted.

So now we need an llmpack like we did webpack? Could it be smart enough to truncate comments, white space, etc?

You dont even need an llm for trimming whitespace, just a smart parser with language rules like ide code checkers already use. Existing llms are fine at summarizing comments, especially with language specific grammar constraints.

My point. We don’t need the middleware.

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

#254

Post by boppo1 »

oceanplexian wrote: post #244
roughly wrote: post #106

Earlier quoted context omitted.

That’s interesting. I tend to lump FB, Amazon, Google, and MS in my head when thinking about the tech giants, but you’re right, FB is the only one of those not offering a commercial platform. For them, building out the capabilities of the LLMs is something to be done in the open with community involvement, because they’re not going to monetize the models themselves. They’re also getting a fantastic amount of press fr…

FB is unlike the other BigTech(tm) since Zuck never sold out and has a controlling equity stake. Amazon, Google, and MS are all controlled by and beholden to institutional investors. FB can release these for no other reason than Zuck’s ego or desire to kill OpenAI. Same deal as him going off on a tangent with the Metaverse thing.

Wonder why Zuck particularly wants to kill OpenAI instead of increasing revenue with a new product offering.

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

#255

Post by jerrysievert »

mchiang wrote: post #240
jerrysievert wrote: post #233

Earlier quoted context omitted.

while it supports it, so far I've only managed to get infinite streams of near nonsense from the ollama models (codellama:7b-q4_0 and codellama:latest) my questions were asking how to construct an indexam for postgres in c, how to write an r-tree in javascript, and how to write a binary tree in javascript.

still modifying the code completion (foundation / python models) to see what's causing the behavior. Have had some good success with the instruct model: codellama:7b-instruct

thanks! this give me some results, but I've had to use a specific construct to get anything meaningful:

using write me a

it's managed to spit out code, rather than "write a traversal function".

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

#256

Post by kordlessagain »

carbocation wrote: post #234
jerrysievert wrote: post #233

Earlier quoted context omitted.

while it supports it, so far I've only managed to get infinite streams of near nonsense from the ollama models (codellama:7b-q4_0 and codellama:latest) my questions were asking how to construct an indexam for postgres in c, how to write an r-tree in javascript, and how to write a binary tree in javascript.

Similarly, I had it emit hundreds of blank lines before cancelling it.

What fortune, I so happen to need hundreds of blank lines.

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

#257

Post by jph00 »

lolinder wrote: post #22
jspisak wrote: post #10

Earlier quoted context omitted.

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

Sorry—who are you and what are the Connect talks? I haven't heard of them and you don't have a bio.

That'll be Joseph Spisak, Head of Generative AI Open Source at Meta AI.

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

#258

Post by sroussey »

mediaman wrote: post #249
kapp_in_life wrote: post #147

Earlier quoted context omitted.

Likely trained on internal code.

That model is trained on synthetically AI-generated code, not internal code. It suggests that synthetic training could be the future in increasing capability of smaller models (and perhaps bigger ones too). AI will train AI.

That is the basis for https://synthesis.ai/

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

#260

Post by sroussey »

boppo1 wrote: post #254
oceanplexian wrote: post #244

Earlier quoted context omitted.

FB is unlike the other BigTech(tm) since Zuck never sold out and has a controlling equity stake. Amazon, Google, and MS are all controlled by and beholden to institutional investors. FB can release these for no other reason than Zuck’s ego or desire to kill OpenAI. Same deal as him going off on a tangent with the Metaverse thing.

Wonder why Zuck particularly wants to kill OpenAI instead of increasing revenue with a new product offering.

They could always spin it out as a separate company.
Post reply on HN