llama
llama copied to clipboard
meta-llama
Save bandwidth by using a torrent to distribute more efficiently
Hi @ChristopherKing42!
Thank you for your pull request and welcome to our community.
Action Required
In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.
Process
In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.
Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.
If you have received this in error or have any questions, please contact us at [email protected]. Thanks!
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!
At this point Meta should publish the original checksums so that we know if it's the real model. It appears that PyTorch models can execute arbitrary code, so this might as well be a clever attack..
Could've helped with.. uh.. reducing bandwidth, but don't have enough space for the entire model, anyone else distributing the load?
At this point Meta should publish the original checksums so that we know if it's the real model. It appears that PyTorch models can execute arbitrary code, so this might as well be a clever attack..
Just convert them to safetensors on a VM or cloud computer.
@d9j I am being told by my source that it takes like 20 minutes to find peers. I have not yet tried it myself though since it isn't official until this pull request gets merged.
this is the best thing i've seen in quite a while thank you for the laughs
At this point Meta should publish the original checksums so that we know if it's the real model. It appears that PyTorch models can execute arbitrary code, so this might as well be a clever attack..
The community came through in #87 🫡
looks like some people have been complaining about the link. it will need more seeders before we can merge into main
Do people really do code reviews where they just say "LGTM"? What's the point of doing a review like that in the first place?