Upload model

modeling_t5mimo.py

@@ -1325,7 +1325,7 @@ class T5MIMOForConditionalGeneration(T5PreTrainedModel):
  self.decoder = T5Stack(decoder_config, self.shared)
 
 
- # self.conv_block = MultivariateConvBlock(config)
+ self.conv_block = MultivariateConvBlock(config)
  self.lm_head = nn.Linear(config.d_model, config.vocab_size, bias=False)
 
  # Initialize weights and apply final processing
@@ -1518,8 +1518,8 @@ class T5MIMOForConditionalGeneration(T5PreTrainedModel):
  sequence_output = decoder_outputs[0]
 
 
- # if use_conv:
- # sequence_output = self.conv_block(sequence_output)
+ if use_conv:
+ sequence_output = self.conv_block(sequence_output)
  
  # Set device for model parallelism
  if self.model_parallel: