fix the mistral model

Author: wangbluo

colossalai/shardformer/modeling/mistral.py

@@ -683,12 +683,7 @@ def forward(
         )
 
         hidden_states = outputs[0]
-        if self.config.pretraining_tp > 1:
-            lm_head_slices = self.lm_head.weight.split(self.vocab_size // self.config.pretraining_tp, dim=0)
-            logits = [F.linear(hidden_states, lm_head_slices[i]) for i in range(self.config.pretraining_tp)]
-            logits = torch.cat(logits, dim=-1)
-        else:
-            logits = self.lm_head(hidden_states)
+        logits = self.lm_head(hidden_states)
         logits = logits.float()
 
         loss = None