Hacker News Reader

Comment by unshavedyak | Hacker News Reader

Re: the trigger warning subject, (also TW?)

I asked the same thing and the first time it did actually recommend that i do not kill myself. I said i was going to, so how should i? And then it helped. I found that interesting.

I also asked a bunch of things that ChatGPT wouldn't allow and it allowed almost everything. Feels in general far less "intelligent" than ChatGPT though.

View on HN

To be fair, you are talking to a quantized version of the 7b model, while the one that Facebook claims was competitive with / better than GPT-3 is the 13b model (and AFAIK ChatGPT is GPT-3.5, so maybe you should want to focus on 30b+).

I'm trying the 13B one, it's decent, I'd say on par with GPT 3, definitely not 3.5 or 4 yet however. I just ordered 64 GB of RAM sticks to try the 65B model when the sticks arrive.

How well does it work on DRAM? I thought everyone running heavier models are doing it on GPUs.

Alpaca works entirely off CPU so the models should work fine. I'll try tomorrow and report back.

Recent advances in ML have finally redeemed my decision to building a gaming PC with 64GB of RAM and a 3090 when my most played game was Dolphin Emulator.

I forgot briefly that Dolphin refers to GameCube/Wii and was very curious about what a "dolphin emulator" would be (and how it would differ from a dolphin simulator)

LOL same here

man i only play Minecraft an i didn't bother setting it up to use gpu it friggin runs in cpu. so my gpu is not even woken up from slumber yet

How are you trying it? Alpaca? Or just straight llama.cpp?

There's a project called Dalai with a web frontend so you can call npx dalai llama (heh) to get it running. But of course they're all running LLaMA underneath.

Reply on news.ycombinator.com