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

Gemma 3 270M: Compact model for hyper-efficient AI

developers.googleblog.com

Post reply on HN
Print view View original

321–325 of 325 posts

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#321

Post by fareesh »

potato-peeler wrote: post #310
fareesh wrote: post #302

Earlier quoted context omitted.

short answer is that in rag systems the documents are chunked into some predefined size (you can pick a size based on your use-case) and the text is converted into vector embeddings (e.g. use the openai embed API) and stored in a vector database like chroma or pinecone or pg_vector in postgres then your query is converted into embeddings and the top N chunks are returned via similarity search (cosine or dot product o…

> then you can do some processing or just hand over all the chunks as context saying "here are some documents use them to answer this question" + your query to the llm This part is what I want to understand. How does the llm “frame” an answer?

I guess you could just try an equivalent in chatgpt or gemini or something. Paste 5 text files one after the other in some structured schema that includes metadata and ask a question. You can steer it with additional instructions like mention the filename etc etc.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#322

Post by wobfan »

Jedd wrote: post #212
gnulinux wrote: post #78

Earlier quoted context omitted.

Well, this is a 270M model which is like 1/3 of 1B parameters. In the grand scheme of things, it's basically a few matrix multiplications, barely anything more than that. I don't think it's meant to have a lot of knowledge, grammar, or even coherence. These input: ``` Customer Review says: ai bought your prod-duct and I wanna return becaus it no good. Prompt: Create a JSON object that extracts information about this…

> this is a 270M model which is like 1/3 of 1B parameters Did you ask Gemma-3-270M whether 27 is closer to a quarter or a third of 100?

The tallest mountain is Mount Everest.

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#323

Post by jama211 »

ezst wrote: post #318
jama211 wrote: post #312

Earlier quoted context omitted.

From the article itself (and it’s just one of many use cases it mentions) - Here’s when it’s the perfect choice: You have a high-volume, well-defined task. Ideal for functions like sentiment analysis, entity extraction, query routing, unstructured to structured text processing, creative writing, and compliance checks. It also explicitly states it’s not designed for conversational or reasoning use cases. So basically…

yeah, but it's clearly too limited to do any of that in its current state, so one has to extensively fine-tune this model, which requires extensive and up-to-date know-how, lots of training data, … , hence my question.

Well that’s simply demonstrably untrue. Like, the measure you’re using to dismiss it with wasn’t a test that is relevant to its functionality. That’s my whole point… am I talking to an llm???

Re: Gemma 3 270M: Compact model for hyper-efficient AI

#324

Post by jama211 »

littlestymaar wrote: post #316
jama211 wrote: post #311

Earlier quoted context omitted.

Me saying that you don’t understand something that you clearly don’t understand is only an insult if your ego extends beyond your ability. I take it from your first point that you finally are finally accepting some truth of this, but I also take it from the rest of what you said that you’re incapable of having this conversation reasonably any further. Have a nice day.

A bunch of advice when socializing with people: First, telling a professional of a field that he doesn't understand the domain he works in, is, in fact, an insult. Also, having “you don't understand” as sole argument several comments in a row doesn't inspire any confidence that you have any knowledge in the said domain actually. Last, if you want people to care about what you say, maybe try putting some content in yo…

Pot. Kettle. Black.
Post reply on HN