-
Notifications
You must be signed in to change notification settings - Fork 155
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Known Issue: Transformers 4.35+ Serialization Issues #786
Labels
transformers-neuronx
transformers-neuronx decoder-only LLM inference
Comments
hannanjgaws
added
the
transformers-neuronx
transformers-neuronx decoder-only LLM inference
label
Nov 9, 2023
Yes, I also bumped into this problem. |
dennj
added a commit
to dennj/transformers-neuronx
that referenced
this issue
Nov 27, 2023
dennj
added a commit
to dennj/transformers-neuronx
that referenced
this issue
Nov 27, 2023
Hello, I made a pull request for a CR to add support for safetensors in |
Safe tensor loads are now fully supported in transformer_neuronx - closing. Please re-open if there are further issues |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
In versions of
transformers>=4.35
model.save_pretrained
serializes models assafetensors
instead ofpytorch_model.bin
files by default. This change breaks thePretrainedModel.from_pretrained
andsave_pretrained_split
methods intransformers-neuronx
, since they expect apytorch_model.bin
file.This issue can be avoided by using an older
transformers
version:This limitation will be addressed in a future Neuron release.
The text was updated successfully, but these errors were encountered: