llama
llama copied to clipboard
Download weights from huggingface to help us save bandwith
The torrent seed is extremely slow this should definitely help out
Hi @Jainam213!
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!
This will save so much bandwidth. Thanks!
LGTM
:rocket: LGTM :rocket: :rocket:
it’s a dataset rather than a model?
Its uploaded as a dataset but check our the files the weights are there
The repository shows that it has been lost. Is there a problem?
Unlike torrents, Huggingface repos arent immutable, and Meta has been pressuring HF to remove repos that contain LLaMA models, so just try focusing effort on seeding the main torrent.
Just to be clear. There is no legal reason why Huggingface removed these weights. (As weights are not copyrightable). They are just doing this to be on the good side of Meta.
How could be loaded a pytorch model if we had separated .pth files for the weights?
I guess uploading to other sources may be an option too :smile: Unfortunately most people don't have servers with a connection beefy enough to support this.
LGTM
😮 😸
LLAMA 2 weights are now on HF