Skip to content

convert_lora_to_gguf: support Qwen3.5/3.8 multimodal LoRA #27995

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.

Sign up for GitHub

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

Closed
the-pgh-cid wants to merge 1 commit into from
Closed

convert_lora_to_gguf: support Qwen3.5/3.8 multimodal LoRA #27995

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions convert_lora_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,6 +273,12 @@ def get_base_tensor_name(lora_tensor_name: str) -> str:
# models produced by mergekit-extract-lora have token embeddings in the adapter
base_name = base_name.replace(".lora_embedding_A", ".weight")
base_name = base_name.replace(".lora_embedding_B", ".weight")
# Multimodal conditional-generation bases (e.g. Qwen3_5ForConditionalGeneration)
# nest the language stack under `model.language_model.layers.N...`; the base
# converter strips `language_model.` (convert_hf_to_gguf.py). Without this
# strip the LoRA tensor names cannot be mapped and conversion fails with
# "Can not map tensor".
base_name = base_name.replace("model.language_model.", "model.")
return base_name


Expand Down