llama.cpp
6eff5932 - convert : handle per_layer_config in Gemma4 (transformers 5.15) (#26882)

Commit
12 hours ago
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>
Author
Parents
Loading