Skip to content

Fix #7924: Error while converting BERT to GGUF: Can not map tensor 'bert.embeddings.LayerNorm.beta' #7926

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

Open
wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Fix #7924: Error while converting BERT to GGUF: Can not map tensor 'bert.embeddings.LayerNorm.beta' #7926

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
42c90d2
fix issue #7924
Wheelspawn Jun 13, 2024
edb1cca
Revert "fix issue #7924"
Wheelspawn Jun 13, 2024
f5e2558
fix issue #7924
Wheelspawn Jun 13, 2024
a0c5a0e
fix line
Wheelspawn Jun 13, 2024
7a5d932
move changes from local to BertModel
Wheelspawn Jun 14, 2024
da43a54
rename normalization layers
Wheelspawn Jun 18, 2024
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
12 changes: 9 additions & 3 deletions convert-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2191,12 +2191,18 @@ def phantom(tok):

def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
del bid # unused


name = name.removeprefix("bert.")

# we are only using BERT for embeddings so we don't need the pooling layer
if name in ("embeddings.position_ids", "pooler.dense.weight", "pooler.dense.bias"):
if name in ("embeddings.position_ids", "pooler.dense.weight", "pooler.dense.bias") or "cls." in name:
return [] # we don't need these

return [(self.map_tensor_name(name), data_torch)]
name = name.replace("gamma", "weight")
name = name.replace("beta", "bias")

try_suffixes = (".weight", ".bias", ".beta", ".gamma")
return [(self.map_tensor_name(name, try_suffixes), data_torch)]


@Model.register("NomicBertModel")
Expand Down