Use nn.GELU for GELU. Runs a bit faster

model.py

@@ -11,14 +11,6 @@
                   'sophiag': SophiaG
                  }
 
-# @torch.jit.script # good to enable when not using torch.compile, disable when using (our default)
-def new_gelu(x):
-    """
-    Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT).
-    Reference: Gaussian Error Linear Units (GELU) paper: https://arxiv.org/abs/1606.08415
-    """
-    return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
-
 class LayerNorm(nn.Module):
     """ LayerNorm but with an optional bias. PyTorch doesn't support simply bias=False """
 
@@ -80,12 +72,13 @@ class MLP(nn.Module):
     def __init__(self, config):
         super().__init__()
         self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
+        self.gelu    = nn.GELU()
         self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
         self.dropout = nn.Dropout(config.dropout)
 
     def forward(self, x):
         x = self.c_fc(x)
-        x = new_gelu(x)
+        x = self.gelu(x)
         x = self.c_proj(x)
         x = self.dropout(x)
         return x