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

InternLM – new open source 7B LLM

github.com

Post reply on HN
Print view View original

31–40 of 93 posts

Re: InternLM – new open source 7B LLM

#31

Post by cubefox »

RobotToaster wrote: post #26
cubefox wrote: post #24

Earlier quoted context omitted.

The most powerful available foundation model is code-davinci-002, a.k.a. GPT-3.5. It's only available on Azure since OpenAI removed it from their own Playground and API for some reason.

The model isn't available at all?

It is available in the sense that it is accessible. The weights are not available for download of course, but the OP wanted to "play around" with it, for which only access is required. There is no other accessible foundation model that can compete with GPT-3.5.

Re: InternLM – new open source 7B LLM

#32

Post by SahAssar »

rfoo wrote: post #15
jabbany wrote: post #10

Earlier quoted context omitted.

Seems pretty common though, for defining custom architecture configs whatnot? AFAIK the "remote code" is still openly hosted on huggingface so you can audit it if you like. Seems no more dangerous than things like `pip install some_random_library`?

I like this pip metaphor. If we had required `--trust-remote-code` for every `npm install` we could have avoided left-pad and most of the software supply chain drama in the past years.

How would that have avoided left-pad? Do you just mean that people would have been discouraged from pulling in so many dependencies?

Re: InternLM – new open source 7B LLM

#33

Post by LightBug1 »

exizt88 wrote: post #30
ohgodplsno wrote: post #17

Earlier quoted context omitted.

Less excited that you can't freely take work from academics to resell it in a shitty SaaS company ?

You do understand that academics are usually funded by taxpayers? Obviously, not by me, as I don't pay taxes in China, but it's not like academics are doing this work for free. Society pays them for their work so that it can benefit from its results.

"Society"

quiet chuckle

Re: InternLM – new open source 7B LLM

#34

Post by blitzar »

ohgodplsno wrote: post #17
exizt88 wrote: post #13

> The code in this repository is open-source under the Apache-2.0 license. The InternLM weights are fully open for academic research and also allow commercial use with written permission from the official team. For inquiries about commercial licenses and collaborations, please contact internlm@pjlab.org.cn. This makes me much less excited about this model.

Less excited that you can't freely take work from academics to resell it in a shitty SaaS company ?

Less excited that I can't freely take work from someone, create a startup that is going to resell it in a shitty SaaS company and cash out for a half B. Yes, yes I am.

Re: InternLM – new open source 7B LLM

#35

Post by blitzar »

freediver wrote: post #12

Tried it with a few PyLLMs benchmarks [1] and it did not do very well. Q. Use m to substitute p, a to substitute e, n to substitute a, g to substitute c, o to substitute h, how to spell peach under this rule? A. m: p a: e n: a g: c o: h how: peach Q. write three sentences each ending with the word apple A. 1. The apple tree was covered in apples. 2. She sliced the apple with a knife. 3. The apple juice was too sweet.…

“when a measure becomes a target, it ceases to be a good measure”

The model itself it optimising weights for its targets, and the model builders are optimising the model for the benchmarks.

Re: InternLM – new open source 7B LLM

#36

Post by version_five »

ohgodplsno wrote: post #17
exizt88 wrote: post #13

> The code in this repository is open-source under the Apache-2.0 license. The InternLM weights are fully open for academic research and also allow commercial use with written permission from the official team. For inquiries about commercial licenses and collaborations, please contact internlm@pjlab.org.cn. This makes me much less excited about this model.

Less excited that you can't freely take work from academics to resell it in a shitty SaaS company ?

So you don't use open source software? You should try it, there's a great ecosystem of free software, including lots written by academics who are happy to have their work add value to industry

Re: InternLM – new open source 7B LLM

#37

Post by version_five »

exizt88 wrote: post #13

> The code in this repository is open-source under the Apache-2.0 license. The InternLM weights are fully open for academic research and also allow commercial use with written permission from the official team. For inquiries about commercial licenses and collaborations, please contact internlm@pjlab.org.cn. This makes me much less excited about this model.

Agreed, this basically moves it to the "don't bother" pile. There are already the llama variants with non-commercial licenses, and open-llama as an open source model (I'm thinking in the 7B space specifically). This would have to be pretty friggin compelling to spend any time on.

Re: InternLM – new open source 7B LLM

#38

Post by alach11 »

cubefox wrote: post #24
gnrlst wrote: post #3

Is this also censored/nerfed? I'd love to play with a "raw" unnerfed model to fully grasp what an LLM can do (and see how biased it is). Does anyone have any recommendations for unnerfed models to try out?

The most powerful available foundation model is code-davinci-002, a.k.a. GPT-3.5. It's only available on Azure since OpenAI removed it from their own Playground and API for some reason.

Maybe you mean gpt-3.5-turbo or text-davinci-003? Or GPT-4 (technically in beta so not fully available to everyone)?

Re: InternLM – new open source 7B LLM

#39

Post by m3affan »

rfoo wrote: post #14
tyfon wrote: post #4

> trust_remote_code=True This is a hard no from me, anyone know why this is so common in models from China? I'm not getting into conspiracies or anything here, but I've seen it in quite a few others from there. I wouldn't run a model with this requirement from anyone else for that matter.

That's because the model architecture hasn't been added to huggingface/transformers yet, because it literally was just published today. >>> from transformers import AutoTokenizer, AutoModel >>> model = AutoModel.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True, device='cuda') Here, the "trust_remote_code=True" means "download the model code from huggingface repo 'internlm/internlm-chat-7b'", along…

Interesting attack vector. Malicious model codes.

Re: InternLM – new open source 7B LLM

#40

Post by oars »

rfoo wrote: post #14
tyfon wrote: post #4

> trust_remote_code=True This is a hard no from me, anyone know why this is so common in models from China? I'm not getting into conspiracies or anything here, but I've seen it in quite a few others from there. I wouldn't run a model with this requirement from anyone else for that matter.

That's because the model architecture hasn't been added to huggingface/transformers yet, because it literally was just published today. >>> from transformers import AutoTokenizer, AutoModel >>> model = AutoModel.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True, device='cuda') Here, the "trust_remote_code=True" means "download the model code from huggingface repo 'internlm/internlm-chat-7b'", along…

Thank you for the explanation.
Post reply on HN