Skip to content

convert : fix tensor naming conflict for llama 4 vision #13836

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

Merged
merged 2 commits into from
May 28, 2025
Merged

convert : fix tensor naming conflict for llama 4 vision #13836

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6af5deb
convert : fix tensor naming conflict for llama 4 vision
ngxson May 27, 2025
6fd1933
add comment
ngxson May 27, 2025
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
3 changes: 3 additions & 0 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2169,6 +2169,9 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
# process vision tensors
if "positional_embedding_vlm" in name and ".weight" not in name:
name += ".weight"
if "multi_modal_projector.linear_1" in name:
# despite the name with number postfix, this is a single fully connected layer
return [(gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.V_MMPROJ_FC], data_torch)]
return [(self.map_tensor_name(name), data_torch)]
return []

Expand Down
1 change: 0 additions & 1 deletion gguf-py/gguf/tensor_mapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -902,7 +902,6 @@ class TensorNameMap:

MODEL_TENSOR.V_MMPROJ_FC: (
"model.connector.modality_projection.proj", # SmolVLM
"multi_modal_projector.linear_1", # llama 4
),

MODEL_TENSOR.V_MMPROJ_MLP: (
Expand Down