tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove .attention from skipped tensors to match more accurately (#7051)

Browse Source
This commit is contained in:
Bartowski
2024-05-02 19:49:09 -04:00
committed by GitHub
parent 6ecf3189e0
commit 60325fa56f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
convert-hf-to-gguf.py
View File

@ -1427,7 +1427,7 @@ class LlamaModel(Model):
experts = dict() experts = dict()
for name, data_torch in self.get_tensors(): for name, data_torch in self.get_tensors():
# we don't need these # we don't need these
if name.endswith((".attention.masked_bias", ".attention.bias", ".attention.rotary_emb.inv_freq")): if name.endswith((".attention.masked_bias", ".attention.bias", ".rotary_emb.inv_freq")):
continue continue
old_dtype = data_torch.dtype old_dtype = data_torch.dtype