StableLM Zephyr 3B • Hacker News Board

Re: StableLM Zephyr 3B

#21

Post by filterfiber » Thu, Dec 07, 2023, 9:01 PM UTC

emadm wrote: post #13

simonw wrote: post #6

"This model is being released under a non-commercial license that permits non-commercial use." I'm very interested in high quality 3B models, but it's hard to get excited about this given the increasing array of commercially usable models.

It will be included under our membership next week which starts at $1 a month after grant ($20 base)

After the Unity re-licensing fiasco, and OpenAI yanking old models,

is there any protections in place to allow the use of StableLM-Zephyr-3B indefinitely or will you be able to just deny any continuing access to models?

Re: StableLM Zephyr 3B

#22

Post by Version467 » Thu, Dec 07, 2023, 9:04 PM UTC

stavros wrote: post #16

Am I reading it right that performance was roughly comparable with GPT-3.5? How is this even possible?

Not really. They already chose to show the benchmark where it does best and even then it’s still quite a bit worse (though definitely impressive for its size). If you take a look at other benchmarks, for example MMLU@5-shot then this does 46.3, while gpt-3.5 does 70.

But there might be some use cases where this one is close enough in performance and the difference in cost and speed make it a better choice.

Re: StableLM Zephyr 3B

#23

Post by nextworddev » Thu, Dec 07, 2023, 9:11 PM UTC

Stability is apparently up for sale, hence the recent steady stream of releases

Re: StableLM Zephyr 3B

#24

Post by supermatt » Thu, Dec 07, 2023, 9:11 PM UTC

This space is so confusing when it comes to licenses.

“Zephyr” is MIT, but “Stability Zephyr” is non commercial. They could have at least used a different name.

“Inspired” in all but license it would seem

Re: StableLM Zephyr 3B

#25

Post by ilaksh » Thu, Dec 07, 2023, 9:23 PM UTC

emadm wrote: post #13

simonw wrote: post #6

"This model is being released under a non-commercial license that permits non-commercial use." I'm very interested in high quality 3B models, but it's hard to get excited about this given the increasing array of commercially usable models.

It will be included under our membership next week which starts at $1 a month after grant ($20 base)

Can you link to an explanation of how membership and licensing works for commercial use?

Re: StableLM Zephyr 3B

#26

Post by emadm » Thu, Dec 07, 2023, 9:29 PM UTC

makin wrote: post #15

emadm wrote: post #13

Earlier quoted context omitted.

It will be included under our membership next week which starts at $1 a month after grant ($20 base)

The parent comment was referring to free ($0 a month) models. With those, companies don't need to plan around the possibility that Stability AI hikes up the price afterwards.

It’ll be static with cpi max, flat membership for all core models

Just released video, sdxl turbo and 3d, code and more coming

Very positive reaction so far and we will still do our grants for OSS and do OSS collaborations, done over 10m A100 hours over last year

Launches next few days https://x.com/emostaque/status/1732197072290353455?s=46

Re: StableLM Zephyr 3B

#27

Post by emadm » Thu, Dec 07, 2023, 9:30 PM UTC

filterfiber wrote: post #21

emadm wrote: post #13

Earlier quoted context omitted.

It will be included under our membership next week which starts at $1 a month after grant ($20 base)

After the Unity re-licensing fiasco, and OpenAI yanking old models, is there any protections in place to allow the use of StableLM-Zephyr-3B indefinitely or will you be able to just deny any continuing access to models?

We looked at that, will be self service for commercial with flat pricing including all base models, weights are all downloadable by anyone.

Models are very interesting

Re: StableLM Zephyr 3B

#28

Post by emadm » Thu, Dec 07, 2023, 9:32 PM UTC

filterfiber wrote: post #17

> Hardware: StableLM Zephyr 3B was trained on the Stability AI cluster across 8 nodes with 8 A100 80GBs GPUs for each nodes. I might be missing it but do they say the number of training tokens that was used to train this? This would help with efforts like TinyLlama in trying to figure out how well the scaling works with training tokens vs parameter size and challenging the chinchilla model.

We included full training details for the base model on 4 trillion tokens including wandb etc

https://stability.wandb.io/stability-llm/stable-lm/reports/S...

Re: StableLM Zephyr 3B

#29

Post by emadm » Thu, Dec 07, 2023, 9:33 PM UTC

filterfiber wrote: post #18

stavros wrote: post #16

Am I reading it right that performance was roughly comparable with GPT-3.5? How is this even possible?

No it's not (according to their benchmarks). Zephyr-7B-B still beats it in most benchmarks but it's close. This model is almost Zephyr-7B-B performance at 3B size which is a lot better for inference requirements.

Yeah got a way to beat 3.5 but it beats most of the first generation llama tunes even guacano 65b

Lots of improvements to go

Re: StableLM Zephyr 3B

#30

Post by mirekrusin » Thu, Dec 07, 2023, 9:35 PM UTC

How those licenses work for generated content? If it's non-commercial does it mean I can still use it for work to generate stuff? In other words - is it similar to ie. using GIMP, which is open source, but I can still use created content in commercial product without attribution?