|
|
@@ -1138,7 +1138,7 @@ class GPT2Model(Model):
|
|
|
|
|
|
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", ".attn.bias")):
|
|
|
+ if name.endswith((".attention.masked_bias", ".attention.bias", ".attention.rotary_emb.inv_freq", ".attn.bias", ".attn.masked_bias")):
|
|
|
continue
|
|
|
|
|
|
if name.endswith((".c_attn.weight", ".c_proj.weight", ".c_fc.weight", ".c_proj.weight")):
|