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

Gemma: New Open Models

blog.google

Post reply on HN
Print view View original

481–490 of 543 posts

Re: Gemma: New Open Models

#481

Post by nl »

phh wrote: post #434
kgeist wrote: post #414

Earlier quoted context omitted.

What prompts/settings do you use for Phi-2? I found it completely unusable for my cases. It fails to follow basic instructions (I tried several instruction-following finetunes as well, in addition to the base model), and it's been mostly like a random garbage generator for me. With Llama.cpp, constrained to JSON, it also often hangs because it fails to find continuations which satisfy the JSON grammar. I'm building a…

My non-domain-specific prompt is: > You are a helpful assistant to 'User'. You do not respond as 'User' or pretend to be 'User'. You only respond once as 'Assistant'. 'System' will give you data. Do not respond as 'System'. Allow yourself inner thoughts as 'Thoughts'. and then I constrain its answers to Thoughts: [^\n]* and Assistant: , and I have two shots included in the prompt. I haven't been able to get anything…

Interesting. I've had no success at all using any of the Phi2 models.

Re: Gemma: New Open Models

#482

Post by int_19h »

noahtallen wrote: post #470
chatmasta wrote: post #371

Earlier quoted context omitted.

Exactly. Sure this particular example is driven by political rage, but the underlying issue is that the maintainers of these models are altering them to conform to an agenda. It's not even surprising that people choose to focus on the political rage aspect of it, because that same political rage is the source of the agenda in the first place. It's a concerning precedent to set, because what other non-political modifi…

Well, every model is altered to conform to an agenda. You will train it on data, which you have personally picked (and is therefore subject to your own bias), and you'll guide its training to match the goal you wish to achieve with the model. If you were doing the training, your own agenda would come into play. Google's agenda is to make something very general that works for everyone. So if you're trying to be as unb…

I'm pretty sure that this whole story with Gemini and now this has already seriously harmed how people trust and rely on those models way more than any implicit biases from the training data.

Re: Gemma: New Open Models

#483

Post by efilife »

alekandreev wrote: post #60
zitterbewegung wrote: post #6

Earlier quoted context omitted.

Do you have a plan of releasing higher parameter models?

We have many great things in research and development phases, so stay tuned. I’m hopeful we can share more in the coming weeks and month!

This doesn't answer the question at all

Re: Gemma: New Open Models

#485

Post by int_19h »

cooper_ganglia wrote: post #275
robswc wrote: post #257

I personally can't take any models from google seriously. I was asking it about the Japanese Heian period and it told me such nonsensical information you would have thought it was a joke or parody. Some highlights were "Native American women warriors rode across the grassy plains of Japan, carrying Yumi" and "A diverse group of warriors, including a woman of European descent wielding a katana, stand together in camar…

I wonder if they have a system prompt to promote diversity in outputs that touch on race at all? I’ve seen several instances of people requesting a photo of a specific people, and it adds in more people to diversify. Not inherently bad, but it is if it forces it to provide incorrect answers like in your example.

It seems to be doing it for all outputs that depict people, in any context.

Re: Gemma: New Open Models

#486

Post by int_19h »

laurentlb wrote: post #453
robswc wrote: post #348

Earlier quoted context omitted.

Gemini. I first asked it to tell me about the Heian period (which it got correct) but then it generated images and seemed to craft the rest of the chat to fit that narrative. I mean, just asking it for a "samurai" from the period will give you this: https://g.co/gemini/share/ba324bd98d9b >A non-binary Indigenous American samurai It seems to recognize it's mistakes if you confront it though. The more I mess with it th…

It's funny how they introduced a clear US-centric bias while trying to push for more diversity.

It's ironic that even the cultural left in US is not immune to American exceptionalism.

Re: Gemma: New Open Models

#488

Post by jppittma »

ranyume wrote: post #429
ben_w wrote: post #201

Earlier quoted context omitted.

> End-users should also be aware of what thoughts are permitted in these constructs. Why omit this information? Can you define that in a way that's actually testable? I can't, and I've been thinking about "unthinkable thoughts" for quite some time now: https://kitsunesoftware.wordpress.com/2018/06/26/unlearnable...

Not OP, but I can think of a few: * List of topics that are "controversial" (models tend to evade these) * List of arguments that are "controversial" (models wont allow you to think differently. For example, models would never say arguments that "encourage" animal cruelty) * On average, how willing is the model to take a neutral position on a "controversial" topic (sometimes models say something along the lines of "t…

They will encourage animal cruelty if the alternative is veganism.

Re: Gemma: New Open Models

#489

Post by reissbaker »

catchnear4321 wrote: post #440
reissbaker wrote: post #410

Earlier quoted context omitted.

It's a local model, they can't turn it off. It's files on your computer without network access.

but what if they send a lawyer to ask firmly? (kindly, but firmly.)

They'd need to send a lot of lawyers, considering that they have no idea how many people are using the model, and very little way of finding out. And they'd need a TOS violation. It would be generally expensive for them to do at scale; this isn't about "turning it off" arbitrarily, it's a CYA in case someone specific does something really bad that makes Google look bad: Google can patch the model to make it not comply with the bad request, and then demand the person running the model update or else lose their license to use the product. It's a scalpel, not an off switch.

Re: Gemma: New Open Models

#490

Post by sanroot99 »

michaelt wrote: post #198
OJFord wrote: post #59

Earlier quoted context omitted.

It really should shouldn't it? I'm quite ML-naïve, but surely providing the model without 'training code or training data' is just like providing a self-hostable binary without the source code? Nobody calls that open source, it's not even source available.

It is widely believed (and in some cases acknowledged) that a lot of models are trained on copyrighted data scraped from the web. In some cases, even scrapes of ebook piracy websites - google 'books3' to learn more. Some companies (such as those working on AI) believe this is legal, others (such as the copyright holders to those books) believe it isn't. In any case, IMHO it's unlikely any cutting edge models will be…

Can training data be generated from llm,with right prompt?
Post reply on HN