simcop2387/AutoGPTQ
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 1 Wiki Activity

remove override of _resize_attention_mask for llama and opt

Browse source
This commit is contained in:
PanQiWei 2023-04-28 23:08:42 +08:00
parent 1d91fded6c
commit b490ab004e
2 changed files with 0 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
auto_gptq/modeling/llama.py
View file

@ -12,10 +12,5 @@ class LlamaGPTQForCausalLM(BaseGPTQForCausalLM):
["mlp.down_proj"]
]
@staticmethod
def _resize_attention_mask(attention_mask):
attention_mask = [each.unsqueeze(1) for each in attention_mask]
return attention_mask
__all__ = ["LlamaGPTQForCausalLM"]

5
auto_gptq/modeling/opt.py
View file

@ -15,10 +15,5 @@ class OPTGPTQForCausalLM(BaseGPTQForCausalLM):
["fc2"]
]
@staticmethod
def _resize_attention_mask(attention_mask):
attention_mask = [each.unsqueeze(1) for each in attention_mask]
return attention_mask
__all__ = ["OPTGPTQForCausalLM"]