Adding `safetensors` variant of this model
This is an automated PR created with https://huggingface.co/spaces/safetensors/convert
This new file is equivalent to pytorch_model.bin but safe in the sense that
no arbitrary code can be put into it.
These files also happen to load much faster than their pytorch counterpart:
https://colab.research.google.com/github/huggingface/notebooks/blob/main/safetensors_doc/en/speed.ipynb
The widgets on your model page will run using this model even if this is not merged
making sure the file actually works.
If you find any issues: please report here: https://huggingface.co/spaces/safetensors/convert/discussions
Feel free to ignore this PR.
Sorry, not accepting any PRs on Synthia models, to ensure that the model is actually what I trained.. I'm also conscious of supply chain attacks and don't want to leave room for any of that 💩..
Ah, apologies for the confusion, I was only trying to use these safetensors models for exllamav2, in which the conversion script required .safetensors versions of the model. I can grab the converted models in the PR branch, which is public in case others need it.
It looks like the 70B model won't convert though as it's quite large.