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

diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py
index 2f146d7302a7811ff76e8e79cb03dcff0e1b01c5..612aea173644bc59a71f807e52c1c0ab0ad92070 100755 (executable)
--- a/convert-hf-to-gguf.py
+++ b/convert-hf-to-gguf.py
@@ -1427,7 +1427,7 @@ class LlamaModel(Model):
         experts = dict()
         for name, data_torch in self.get_tensors():
             # 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
 
             old_dtype = data_torch.dtype