531–540 of 543 posts
Hello on behalf of the Gemma team! We are really excited to answer any questions you may have about our models. Opinions are our own and not of Google DeepMind.
Earlier quoted context omitted.
Fun that's not my experience of Phi-2. I use it for non-creative context, but function calling, and I find as reliable as much bigger models (no fine-tuning just constraining JSON + CoT). Phi-2 unquantized vs Mixtral Q8, Mixtral is not definitely better but much slower and RAM-hungry.
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…
Earlier quoted context omitted.
Regarding the last one: there 1.5 million immigrants in Norway with total population 5.4 million. Gemini isn't very wrong, is it?
I think its great that some consideration was given by Gemma to the 2.3 million Norwegian immigrants. However it is/was very consistent in which kind of Norwegians it decided to show regardless of the prompt 100% of the time. In fact it was quite adamant regardless of the time period or geography. Rather mysteriously if you try it now as opposed to when it came out the results currently only show non-immigrant Norweg…
Pretending that a shoddy AI image generated with a blatant inability to produce consistent output is a "serious risk" is ridiculous. The thing wasn't even able to give you a picture of the founding fathers that didn't look like a Colors of Benetton ad. I struggle to imagine what tangible risk this "misinfo" would have. Norwegians being the wrong color? And what harm does that do? Bad assumptions about the prevalence of sickle cell anemia?
Earlier quoted context omitted.
Not entirely wrong but there isn't a single German ethnicity, just to be clear. Because of geographic reasons. I've studied that topic in depth, there is genetic data to back it up as well. Germany has almost the same haplogroup makeup as the notoriously heterogenous Belgium, which is to say that there is groups stemming from all surrounding regions. And that traces back about two millenia. It's different from say Ja…
Just like Russians then
This is also true for China, which engages in Han supremacism (as part of the "one China" policy dating back to Mao), and India, which engages in Hindu supremacism.
Arguably Germany also suppresses some of its indigenous ethnicities, although not as blatantly as during the exterminationist policies of the Third Reich. While there are public institutions to preserve the language and culture of the Sorbian, Danish and Frisian minorities for example, Germany unlike e.g. the US has a single official language and merely "recognizes" theirs (i.e. acknowledges their existence but does not require them to be accomodated in areas where they are widely used).
Earlier quoted context omitted.
Wait, who are you again? A 20 day old troll account?
Everyone who isn’t part of your little group is a far-right bigot and troll right? Seeing Google on a resume has been an increasingly mixed signal for about a decade. Ask around. I can only speak for myself: after Gemma these types are radioactive. I’m done. I think you’re in for a rude awakening.
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…
So they made the models blatantly, explicitly racist. Well done.
Earlier quoted context omitted.
That's useful to know. My experiments with the 4bit 7B currently tagged for use on ollama are not going well at all. Lots of refusals and junk. Downloading 7b-instruct-fp16 now! :-) (Update: Yes, much better, though much slower too, of course.)
FYI we have an experimental 4.5-bit format (NUQ) in gemma.cpp, our C++ inference engine, which from my testing works reasonably well.
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.
Earlier quoted context omitted.
Is there any truth behind this claim that folks who worked on Gemma have left Google? https://x.com/yar_vol/status/1760314018575634842
I confirmed all the folks listed on page 12 are still at Google (listed below). I am guessing the linked tweet is a BS claim. # Product Management Tris Warkentin Ludovic Peran # Program Management Minh Giang # Executive Sponsors Clement Farabet Oriol Vinyals Jeff Dean Koray Kavukcuoglu Demis Hassabis Zoubin Ghahramani Douglas Eck Joelle Barral Fernando Pereira Eli Collins # Leads Armand Joulin Noah Fiedel Evan Senter…
Earlier quoted context omitted.
Just like Russians then
The only caveat is that the Soviets essentially tried to manufacture ethnostates by forcibly displacing ethnic groups from one region to another, but yes, Russia is ethnically heterogeneous although there is still a good deal of Slavic supremacism present in Russian politics (e.g. conscription disproportionately affects ethnic minorities because they're generally poorer and unable to avoid it or desperate enough to v…
"Soviets essentially tried to manufacture ethnostates by forcibly displacing ethnic groups from one region to another"
Not really. During the policy of so called "korenizatsiia"[0] (indigenization) Russians were deprived of leadership roles and forced to learn local languages. In the next period Stalin was punishing certain ethnicities for relatively high level of collaboration with Nazis by relocating them to inhospitable regions.
"Russia is ethnically heterogeneous "
I didn't mean Russian citizens, I meant ethnic Russians which themselves are a mixture of god knows what (I'm Russian myself).
"there is still a good deal of Slavic supremacism present in Russian politics (e.g. conscription disproportionately affects ethnic minorities... )"
Many ethnic minorities have better demographics -- they have many more children than ethnic Russians and correspondingly more men of the conscription age.
"This is also true for China, which engages in Han supremacism"
For example, the CCP's draconian 'one family -- one child' policy applied only to Han. [1] Doesn't look like Han supremacism to me.
"Germany unlike e.g. the US has a single official language"
Again, not really: "there is no official language at the federal level Three states and four U.S. territories have recognized local or indigenous languages in addition to English."[2] Three states isn't much for a whole continent inhabited by Native Americans. Or try finding any Native American language or even Spanish on the web site of the US Congress, for example.
[0] https://en.wikipedia.org/wiki/Korenizatsiia#Against_Great-Ru...
[1] https://en.wikipedia.org/wiki/Affirmative_action_in_China