How does the Nemo 12B compare to the Llama 3.1 8B?

Apparently I am an idiot and read the wrong paper. The previous paper mentioned that “comparable with the 8-bit models”

https://huggingface.co/papers/2310.11453

They said their’s is “comparable with the 8-bit models”. Its all tradeoffs. It isn’t clear to me where you allocate your compute/memory budget. I’ve noticed that full 7b 16 bit models often produce better results for me than some much larger quantied models. It will be interesting to find the sweet spot.

So are more bits less important than more paramters? Would a higher paramter or higher bit count matter more if the models ended up the same size?

Sony choose to not offer refunds. Sony knew the contract when they agreed to sell the content. When something gets pulled from steam I can still download and install it.

I hope Mastodon succeeds but I don’t see it taking off like twitter did.

At work we pay Microsoft thousands for developer licensees, have windows pro, and there is still ads in the OS… Windows exists to service them not us.

Stuff like this will be used in the anti monopoly cases going on world wide.

That might be hard unless they start requiring logins.

I canceled when they raised the price. I am DONE with all the price increases the past year.

You can do both

Picture seems to be gone? I don’t know how lemmy works. But here was the picture

https://i.redd.it/7gxwomiq80bb1.png

If you don’t have a good GPU then just use gpt4all

https://gpt4all.io/index.html

aww