1 Commits
Author SHA1 Message Date
6eff593262 convert : handle per_layer_config in Gemma4 (transformers 5.15) (#26882)
* fix: handle nested global_head_dim in Gemma4 config

Gemma-4 E4B models have global_head_dim inside text_config
rather than at the top level. Add fallback to support both layouts.

* fix: add fallback for global_head_dim to support per_layer_config format

* fix: read head_dim only from full_attention layers in per_layer_config and num_global_key_value_heads compatibility

* fix: added fallback for num_global_key_value_heads

* fix: read per_layer_config from root hparams

* fix: delete unused text_config

* cleanup and fixes

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
2026-08-12 08:05:13 +03:00