Llama 2 • Hacker News Board

Re: Llama 2

#851

Post by simbolit » Thu, Jul 20, 2023, 10:58 AM UTC

canttestthis wrote: post #470

jug wrote: post #290

Earlier quoted context omitted.

General consensus if you ask about it is that it's not considered swimming though. I think you'd be looking for locomotion through water without frequent touch downs. This is an example: https://www.nationalgeographic.com/animals/mammals/facts/hip... GPT-4 had a much better answer last I checked. Edit: Updated with another non-paywall link.

After having reviewed the relevant material I think it's fair to say that hippos swim, per our conventional understanding of what swimming is.

And I think it's fair to say they don't, per conventional understanding. Good for both of us.

Re: Llama 2

#852

Post by SysAdmin » Thu, Jul 20, 2023, 11:37 AM UTC

May I ask how many consolidated.0x.pth files are there for llama-2-70b-chat model, please? Or what is the overall size of every .pth file combined together, please?

Thanks very much in advance for any pointers. ^^

Re: Llama 2

#853

Post by zzzzzzzza » Thu, Jul 20, 2023, 12:57 PM UTC

jcuenod wrote: post #845

fnl wrote: post #756

Earlier quoted context omitted.

> OpenAI are doing tricks with the model output Do you have any pointers to the “tricks” that are being applied?

Sounds like a reference to Mixture of Experts

could be something like prompt rewriting or chain of thought or reflexion going on in the background as well

Re: Llama 2

#854

Post by Naracion » Thu, Jul 20, 2023, 2:10 PM UTC

baobabKoodaa wrote: post #770

sangnoir wrote: post #744

Earlier quoted context omitted.

> after all, why would you ship a worse model to prod? ...because you need a control to evaluate how well your product is doing? I know it's a young field, but boy, do some folk love removing the "science" from "data science"

You can evaluate a version of the model that has been trained on one set of data, and ship to production a different model that has been trained on the complete set of data. In many cases one can reasonably infer that the model which has seen all of the data will be better than the model which has seen only some of the data. I'm not claiming that's what happened here, nor am I interested in nitpicking "what counts as…

>infer that the model which has seen all of the data will be better than the model which has seen only some of the data.

It really depends upon the data. A smaller set of data that mostly consists of "truth" might be better than a larger dataset that also has many "lies".

Perhaps what you mean is that the model might be more representative, rather than _better_.

Re: Llama 2

#855

Post by linsomniac » Thu, Jul 20, 2023, 4:08 PM UTC

FYI: There's a playground at https://llama2.ai/

Re: Llama 2

#856

Post by PeterStuer » Thu, Jul 20, 2023, 4:22 PM UTC

foobiekr wrote: post #613

mirekrusin wrote: post #585

Earlier quoted context omitted.

GPT models were internally available 6-12 months before they've seen public beta, of course OpenAI has more capable internal models.

There's no reason to believe this. The training time and cost is so substantial that they are almost certainly building their next release, but it isn't sitting there rotting.

OpenAI themselves have said they hat GPT-4 internally before they ever released the first version of ChatGPT.

Re: Llama 2

#857

Post by amilios » Thu, Jul 20, 2023, 6:15 PM UTC

lpolovets wrote: post #844

amilios wrote: post #843

Earlier quoted context omitted.

Interesting. It worked for me! Response: Early stage venture capital firms typically have a few non-investor roles that are critical to their operations. Here are some of the most common non-investor roles at early stage venture capital firms: Entrepreneur-in-Residence (EIR): An EIR is a seasoned entrepreneur who works closely with the venture capital firm to help identify, develop, and support startups. They often p…

Interesting, thanks for sharing! Just tried again at https://llama.perplexity.ai/ and it worked better this time. I still got the first paragraph about how "non-investor" is a discriminatory/exclusionary term, but then LLaMa provided an answer anyway. (Screenshot: https://ibb.co/1v3D6Wt )

Yeah unfortunately I think this is the result of the stochasticity of sampling from the LLMs with non-zero temperature, it'll give a different answer every time and some answers might trigger the guardrails and others might not. I am curious if the greedy-sampling answer contains the guardrails or not...

Re: Llama 2

#858

Post by b33j0r » Thu, Jul 20, 2023, 8:21 PM UTC

jacquesm wrote: post #488

b33j0r wrote: post #463

Earlier quoted context omitted.

I got that question wrong, I still have no idea what the correct answer would be. That is extremely obscure. Any intelligence or simulation might try to guess at an answer to that third-level-of-hell interrogation. “Why was Spartacus filmed in California near pizza noodle centurions?”

You could of course also answer 'I don't know' which to me is a correct answer, far more so than something you made up.

That would make it a more reasonable human. But it’s actually a compendium of everything you and I and shakespeare and the january 6th viking have penned.

The creativity, which we call hallucination, is the advantage of the approach.

If I wanted a search engine for actionable facts, they have worked pretty well for 30 years.

Re: Llama 2

#859

Post by anticensor » Fri, Jul 21, 2023, 4:52 PM UTC

dmix wrote: post #500

swamp40 wrote: post #447

Earlier quoted context omitted.

Donating a kidney.

I think they mean when a for-profit company does it.

Even then. Nobody is perfect, not even companies.

Re: Llama 2

#860

Post by ISV_Damocles » Tue, Jul 25, 2023, 5:16 PM UTC

CSMastermind wrote: post #332

jug wrote: post #275

Earlier quoted context omitted.

Still fails my hippo test! > Yes, hippos are excellent swimmers. They spend most of their time in the water, where they feed on aquatic plants and escape the heat of the savannah. In fact, hippos are one of the best swimmers among all land mammals. But that's fine. Most do. Hippos don't swim. They walk or hop/skip at best underwater.

There's a few prompts that I use with every model to compare them. One of the simplest ones is: > When does the bowl of the winds get used in the wheel of time books? LLaMA2 fails pretty hard: > The Bowl of the Winds is a significant artifact in the Wheel of Time series by Robert Jordan. It is first introduced in the third book, "The Dragon Reborn," and plays a crucial role in the series throughout the rest of the bo…

So this comment inspired me to write a Roman Numeral to Integer function in out LLM-based programming language, Marsha: https://github.com/alantech/marsha/blob/main/examples/genera...