InternLM – new open source 7B LLM
github.com
InternLM – new open source 7B LLM
1–10 of 93 posts
Re: InternLM – new open source 7B LLM
#2Great name for a simple LLM hehe
Re: InternLM – new open source 7B LLM
#3Is 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?
Re: InternLM – new open source 7B LLM
#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.
Re: InternLM – new open source 7B LLM
#5Is 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?
Re: InternLM – new open source 7B LLM
#6I welcome new models! The more, the merrier.
That said, this model has been tailored but they are comparing it to non-finetuned LLaMA-7B in their benchmark? That seems a bit fainthearted.
Re: InternLM – new open source 7B LLM
#7> 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.
Mind pasting the link to that line? Am on mobile and can’t find it myself easily.
Re: InternLM – new open source 7B LLM
#8A related question -- when fine tuning a model like this to a specific corpus, how does the fine tuning effect the actual chat capability, since the chat model weights seem to come as a separate model? Does one fine tune the LLM+Chat model directly? If so, does that not require some kind of prompt based training as opposed to just lookahead prediction? Does one have to fine tune the LLM and then repeat whatever they do to get the LLM+Chat model?
Re: InternLM – new open source 7B LLM
#9> 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.
I believe it's because the model architecture isn't added to Huggingface transformer library, so it needs to eval some python code (i.e. load a pickle) to create the PyTorch model. Have not noticed it to be specific to models from China, almost all lesser known models have to do this.
Re: InternLM – new open source 7B LLM
#10> 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`?