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

21–30 of 93 posts

Re: InternLM – new open source 7B LLM

#21

Post by Lockal »

jabbany wrote: post #10
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.

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`?

This has become less common in recent days, at least for image generation (e. g. safetensors in Stable Diffusion).

The point of opensource models is that they can be finetuned. When many people create finetuned versions, a zoo of models appear. So far so good (maybe), but the bad practice of using untrusted code from the zoo sooner or later will lead to a wave of cryptominers, ransomware, and credential theft incidents.

Re: InternLM – new open source 7B LLM

#22

Post by rfoo »

tyfon wrote: post #20
rfoo wrote: post #14

Earlier quoted context omitted.

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…

I've only used llama via llama.cpp. In general I think the python ML stuff is a mess. But I still won't execute code that recommend me to trust arbitrary remote code as the remote code can change at any time, it would be better to wait with the release until it was published to the transformers library or just include it in a clonable repo without the trust_remote_code flag. It is much better to just be able to clone…

Yeah, I agree promoting this usage is as bad as promoting `curl | sh` in README.md.

Similar to how you can inspect the content of a `curl | sh` script and then run it, the model is also in a clonable repo, you may just:

   git clone https://huggingface.co/internlm/internlm-7b-chat
and:

    >>> from transformers import AutoTokenizer, AutoModel
    >>> model = AutoModel.from_pretrained("./internlm-chat-7b", device='cuda')

Re: InternLM – new open source 7B LLM

#23

Post by exizt88 »

hmottestad wrote: post #16
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.

Is that even valid? This seems to be the only place where they’ve made this exemption, it’s not written in the license. Even the weights on hugging face are licensed under apache 2.0. Doesn’t apache 2.0 allow for fairly unrestricted commercial use? Isn’t that the whole point of using that license?

The model code is Apache 2.0, the weights are proprietary.

Re: InternLM – new open source 7B LLM

#24

Post by cubefox »

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.

Re: InternLM – new open source 7B LLM

#26

Post by RobotToaster »

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.

The model isn't available at all?

Re: InternLM – new open source 7B LLM

#28

Post by tyfon »

rfoo wrote: post #22
tyfon wrote: post #20

Earlier quoted context omitted.

I've only used llama via llama.cpp. In general I think the python ML stuff is a mess. But I still won't execute code that recommend me to trust arbitrary remote code as the remote code can change at any time, it would be better to wait with the release until it was published to the transformers library or just include it in a clonable repo without the trust_remote_code flag. It is much better to just be able to clone…

Yeah, I agree promoting this usage is as bad as promoting `curl | sh` in README.md. Similar to how you can inspect the content of a `curl | sh` script and then run it, the model is also in a clonable repo, you may just: git clone https://huggingface.co/internlm/internlm-7b-chat and: >>> from transformers import AutoTokenizer, AutoModel >>> model = AutoModel.from_pretrained("./internlm-chat-7b", device='cuda')

This way is much more palpable for me, thank you for showing :)

Re: InternLM – new open source 7B LLM

#29

Post by datastack »

yieldcrv wrote: post #25

why is 7B parameters seemingly a magic number?

I guess going with a parameter count that matches existing models makes it easier to compare benchmarks. Perhaps there is another particular reason like required memory, but momentum is probably also significant.

Re: InternLM – new open source 7B LLM

#30

Post by exizt88 »

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 ?

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.
Post reply on HN