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

Beginner's Guide to Llama Models

agi-sphere.com

Post reply on HN
Print view View original

21–30 of 41 posts

Re: Beginner's Guide to Llama Models

#21

Post by ulnarkressty »

I tried multiple flavors of llama models, they are all quite dumb. Even the 70b parameter one. It knows about more things which the smaller models just hallucinate when asked, but still cannot do even slightly more complex tasks.

I'm also not sure about the current testing methodologies i.e. the 'passed the SAT' hype. Given that the training set already contains much of the information, we should probably compare the AI results with humans having unlimited time and access to the required material.

Re: Beginner's Guide to Llama Models

#22

Post by jmorgan »

yu3zhou4 wrote: post #17

Can you recommend another systematized guides like this about LLMs and ML in general? Even though was quite limited in info, I like the structured and concise form and I’d be happy to learn about similar blog posts

I really enjoyed Anrej Kaparthy's llama2.c project (https://github.com/karpathy/llama2.c), which runs through creating and running a miniature Llama2 architecture model from scratch.

Re: Beginner's Guide to Llama Models

#23

Post by mhaberl »

thatguymike wrote: post #4

I find the whole site being covered in images of skinny waifu girls... offputting. The guide itself seems fine, if high-level. [This]( https://chat.lmsys.org/?leaderboard ) is a really nice link I hadn't seen before.

> skinny waifu girls

I think the idea of the images was a Lama (the animal) and a model (the girl) - Lama models

> The guide itself seems fine

The piece is informative for those new to the subject, but not much beyond that.

Re: Beginner's Guide to Llama Models

#25

Post by xcdzvyn »

jmorgan wrote: post #20

An easy way to try many of the fine-tuned Llama 2 models is https://github.com/jmorganca/ollama . A maintainer of the project has been collecting a full list here (with different quantization levels), most of which are Llama 2-based: https://gist.github.com/mchiang0610/b959e3c189ec1e948e4f6a1f... Since the release of Llama 2 the number of models based on it has been growing significantly.. some popular ones: - codeup…

Wow, thanks! I really like Ollama, so I'm glad the models listed at the top of the Readme aren't all you could use. Do you know where the data in that Gist came from? Is there a registry somewhere?

Re: Beginner's Guide to Llama Models

#26

Post by brabel »

kristofferg wrote: post #13
brabel wrote: post #9

Earlier quoted context omitted.

Same here... the images are beautiful but seem completely unrelated to the topic (other than being AI-generated - but they could've generated images that have some sort of relation to the topic instead!). It kind of shows what the author has been using the AI for, I suppose :P.

I would usually agree but in this case its a pun on “models”. I find it quite funny.

Oh I see... and a "model" is always young, skinny, white and female I guess (cannot blame the AI though, I guess that is what you get if you look at the internet as a whole as your training data).

EDIT: I had to lookup "waifu" and it seems the author probably prompted for "waifu model"(?)... according to Wikipedia, for those like me who are not into that sort of thing:

"A Waifu is an illustrated female character from an anime or any non-live action media in which an individual becomes sexually attracted to."

Re: Beginner's Guide to Llama Models

#27

Post by danielbln »

jmorgan wrote: post #20

An easy way to try many of the fine-tuned Llama 2 models is https://github.com/jmorganca/ollama . A maintainer of the project has been collecting a full list here (with different quantization levels), most of which are Llama 2-based: https://gist.github.com/mchiang0610/b959e3c189ec1e948e4f6a1f... Since the release of Llama 2 the number of models based on it has been growing significantly.. some popular ones: - codeup…

llama2-uncensored is a lot of fun, interacting with an unaligned/uncensored model feels very fresh.

Re: Beginner's Guide to Llama Models

#30

Post by kristofferg »

brabel wrote: post #26
kristofferg wrote: post #13

Earlier quoted context omitted.

I would usually agree but in this case its a pun on “models”. I find it quite funny.

Oh I see... and a "model" is always young, skinny, white and female I guess (cannot blame the AI though, I guess that is what you get if you look at the internet as a whole as your training data). EDIT: I had to lookup "waifu" and it seems the author probably prompted for "waifu model"(?)... according to Wikipedia, for those like me who are not into that sort of thing: "A Waifu is an illustrated female character from…

You are right in that is neither high-brow or PC. :)
Post reply on HN