Update modeling_quiet.py

modeling_quiet.py

@@ -158,7 +158,7 @@ class QuietRMSNorm(nn.Module):
 
     def forward(self, hidden_states):
         input_dtype = hidden_states.dtype
-        hidden_states = hidden_states.to(torch.float32)
+        hidden_states = hidden_states.to(torch.bfloat16)
         variance = hidden_states.pow(2).mean(-1, keepdim=True)
         hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
         return hidden_states.to(input_dtype) * self.weight.to(hidden_states.device)