News for hackers. Stuff that matters.
Re:Large language models are having their Stable Diffusion m... by Roritharr on Saturday March 11, 2023 @07:32PM (#35114748)
I can set top_k, temperature and top_p via shell already, but I don't think repetition penalty is dynamic yet. Looking into it.
Re:Large language models are having their Stable Diffusion m... by eigenvalue on Saturday March 11, 2023 @08:50PM (#35115459)
Thanks for flagging this. Using that repo, I'm getting pretty good results with the following:

./main -m ./models/13B/ggml-model-q4_0.bin -t 7 -b 10 --top_p 0.0 -n 5000 --temp 0.7 --repeat_last_n 64 --repeat_penalty 1.3 --prompt "You are a question answering bot that is able to answer questions about the world. You are extremely smart, knowledgeable, capable, and helpful. You always give complete, accurate, and very detailed responses to questions, and never stop a response in mid-sentence or mid-thought. You answer questions in the following format:

Question: What’s the history of bullfighting in Spain?

Answer: Bullfighting, also known as "tauromachia," has a long and storied history in Spain, with roots that can be traced back to ancient civilizations. The sport is believed to have originated in 7th-century BCE Iberian Peninsula as a form of animal worship, and it evolved over time to become a sport and form of entertainment. Bullfighting as it is known today became popular in Spain in the 17th and 18th centuries. During this time, the sport was heavily influenced by the traditions of medieval jousts and was performed by nobles and other members of the upper classes. Over time, bullfighting became more democratized and was performed by people from all walks of life. Bullfighting reached the height of its popularity in the 19th and early 20th centuries and was considered a national symbol of Spain. However, in recent decades, bullfighting has faced increasing opposition from animal rights activists, and its popularity has declined. Some regions of Spain have banned bullfighting, while others continue to hold bullfights as a cherished tradition. Despite its declining popularity, bullfighting remains an important part of Spanish culture and history, and it continues to be performed in many parts of the country to this day.

Now complete the following questions:

Question: What happened to the field of cybernetics in the 1970s?

Answer: "

Re:Large language models are having their Stable Diffusion m... by Roritharr on Saturday March 11, 2023 @09:15PM (#35115661)
Interesting, that one segfaults for me. Gonna try with fresh eyes tomorrow, thanks!
Re:Large language models are having their Stable Diffusion m... by Retr0id on Saturday March 11, 2023 @10:43PM (#35116368)
> and never stop a response in mid-sentence or mid-thought

I'm curious if this part actually does anything to improve the output, my intuition says it doesn't help much. I don't have it running locally to test yet, though.

Re:Large language models are having their Stable Diffusion m... by aardvarkr on Sunday March 12, 2023 @01:24AM (#35117334)
These prompts become “key pillars” of the LLM’s “identity”. If you are curious you should at look about how much personality MS Sydney acquired through it’s own startup prompt.
Re:Large language models are having their Stable Diffusion m... by dr_dshiv on Sunday March 12, 2023 @06:36AM (#35118550)
Lol, was that blank an accurate answer about cybernetics?
Re:Large language models are having their Stable Diffusion m... by delusional on Sunday March 12, 2023 @07:35AM (#35118945)
That's the prompt, it's where the inserts the stuff it generates. The AI generated content has not been posted.
Re:Large language models are having their Stable Diffusion m... by eigenvalue on Sunday March 12, 2023 @09:41PM (#35129571)
Yes I believe the parent was making a joke :)
Re:Large language models are having their Stable Diffusion m... by alfonsodev on Sunday March 12, 2023 @07:42AM (#35118997)
I think accidentally the bot is kind of correct, you are asking to "complete the following questions" and that question seems complete, maybe the bot could have asked for clarification, I've never had that situation yet, would be something like .. "That question seems very well formulated, do you want me to answer it ? or to complete the question? we could complete the question by being more specific about location, for example what happened to the filed of cybernetics in EEUU in the 1970s ?"
Re:Large language models are having their Stable Diffusion m... by sorokod on Sunday March 12, 2023 @04:28PM (#35125807)
Why would there be medieval jousts in the 17th and 18th centuries?
Re:Large language models are having their Stable Diffusion m... by nsxwolf on Saturday March 11, 2023 @10:02PM (#35116009)
What kind of effort does it take to have any idea what you guys are talking about? Is there a For Dummies book?
Re:Large language models are having their Stable Diffusion m... by enjoylife on Sunday March 12, 2023 @01:20AM (#35117312)
It’s essentially a question of did you take a look the code? There is comments in the codebase directly where the config values in question are being used. Eg.

> # repetition penalty from CTRL paper (https://arxiv.org/abs/1909.05858)

Now I’m assuming a base rate of knowledge for this to help, but in general I find diving into the code paths of open source models, usually is a good use of time.

Re:Large language models are having their Stable Diffusion m... by pksebben on Sunday March 12, 2023 @03:43AM (#35117772)
there's no for dummies, this stuff is too new. there's a bunch of white papers to read; _attention is all you need_ is a good place to start, kinda.

if you troll HN for AI related stuff and just read read read, progressively googling the terms you don't understand, eventually the haze will lift and things will start to make some sense.

source: in the middle of doing that right now

Re:Large language models are having their Stable Diffusion m... by ben_w on Sunday March 12, 2023 @07:03AM (#35118710)
> if you troll HN for AI related stuff and just read read read

Do you mean "troll" or "trawl"?

(I'm thinking of an old saying that the best way to get an answer isn't to ask a question, but to say the thing is impossible. Can't remember it well enough to google for the exact form, however).

Re:Large language models are having their Stable Diffusion m... by Qworg on Sunday March 12, 2023 @07:37AM (#35118967)
IIRC, both forms work.

Trolling is done by hand with a fishing pole, sometimes on a dock.

Trawling is from the back of a boat, generally with a net.

Re:Large language models are having their Stable Diffusion m... by ben_w on Monday March 13, 2023 @04:29AM (#35132725)
Interesting. Until now I only knew the verb "troll" as in "being mean on the internet".
Re:Large language models are having their Stable Diffusion m... by pksebben on Wednesday March 15, 2023 @07:56PM (#35176349)
If I'm not hallucinating like GPT, I think the etymology of troll as in internet actually stems from trolling as in fishing.

I have a hazy recollection of folks in the early days of 4chan describing 'trolling for idiots' - as in, feigning ignorance to get a rise out of folks. Like, you post a dumb, obviously stupid but infuriating comment and watch people get all worked up about it. You know, for the lulz.

I feel like since then it's changed to just actually being a dumb asshole and enjoying when people are mad at you. Or maybe I've just gotten smarter. In any event at the time it certainly didn't seem like the kind of thing racist lunatics would go out of their way to do. Perhaps more the fool I, as I was a teenager at the time and as such that opinion cannot really be trusted.

Re:Large language models are having their Stable Diffusion m... by bootsmann on Sunday March 12, 2023 @04:14AM (#35117929)
I think the best way is to get a basic understanding of torch and then just reading what the code does. The model internals are hard (though for the transformer there are good step by steps online) but for this case it is basically playing with the output of the actual neural net inside the model. The net gives you a probability distribution to be next over all tokens (think words). Now it has proven to be useful not to pick the token with the highest probability but to employ different strategies. Top-k in this case means probabilistically sampling from the top k tokens instead of piking the best.
Re:Large language models are having their Stable Diffusion m... by sirsinsalot on Sunday March 12, 2023 @05:22AM (#35118238)
"Transformers for Natural Language Processing", Denis Rothman (Packt)
Re:Large language models are having their Stable Diffusion m... by d0mine on Sunday March 12, 2023 @05:28AM (#35118257)
To understand how pytorch works (bottom-up with practice video lectures): Neural Networks: Zero to Hero Andrej Karpathy https://youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9Gv...