Skip to content

Conversation

@danieldjohnson
Copy link
Collaborator

Adds some commonly-used but irrelevant attributes to the ignores list for HuggingFace model conversion. Also adds conversion logic for the hidden_act="gelu" case.

Based on the original PR #116 by @ealt.

Fixes #112. Fixes #115.

Fixes #115
Fixes #112

Co-authored-by: Eric Alt <ericallenalt@gmail.com>
@google-cla
Copy link

google-cla bot commented Jun 22, 2025

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

@danieldjohnson
Copy link
Collaborator Author

(Bypassing CLA check here since the CLA already passed for #116)

@danieldjohnson danieldjohnson merged commit aac7808 into main Jun 22, 2025
1 of 2 checks passed
@danieldjohnson danieldjohnson deleted the push-vwyksqvozosx branch June 22, 2025 05:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Conversion from pretrained HuggingFace models Conversion of a LlamaForCausalLM does not support use_cache and _name_or_path

1 participant