zhuzilin
/

gpt2-summarize-sup4_ppo_rm4

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Zilin Zhu commited on Dec 28, 2022

Commit

c042756

·

1 Parent(s): 980d254

fix bug

Files changed (1) hide show

modeling_gpt2_summarize.py +1 -1

modeling_gpt2_summarize.py CHANGED Viewed

@@ -327,7 +327,7 @@ class GPT2Attention(nn.Module):
         if layer_past is not None:
             past_key, past_value = layer_past
-            key = torch.cat((past_key, key), dim=-2)
             value = torch.cat((past_value, value), dim=-2)
         if use_cache is True:

         if layer_past is not None:
             past_key, past_value = layer_past
+            key = torch.cat((past_key, key), dim=-1)
             value = torch.cat((past_value, value), dim=-2)
         if use_cache is True: