Update gpt2.py

gpt2.py

@@ -14,6 +14,7 @@ class CasualSelfAttention(nn.Module):
 
         self.c_attn = nn.Linear(config.n_embd, config.n_embd * 3)
         self.c_proj = nn.Linear(config.n_embd,config.n_embd)
+        self.c_proj.NANOGPT_SCALE_INIT = 1
 
         self.n_head = config.n_head
         self.n_embd = config.n_embd
@@ -48,7 +49,7 @@ class MLP(nn.Module):
         self.c_fc = nn.Linear(config.n_embd,config.n_embd * 4)
         self.gelu = nn.GELU(approximate="tanh")
         self.c_proj = nn.Linear(config.n_embd * 4,config.n_embd)
-
+        self.c_proj.NANOGPT_SCALE_INIT = 1
 
     def forward(self,x):
         x = self.c_fc(x)
@@ -89,6 +90,19 @@ class GPT2(nn.Module):
         #Weight sharing
         self.transformer.wte.weight = self.lm_head.weight
 
+        self.apply(self._init_weights)
+
+    #
+    def _init_weights(self,module):
+        if isinstance(module,nn.Linear):
+            if hasattr(module,"NANOGPT_SCALE_INIT"):
+                std += (2*self.config.n_layer) ** -0.5
+            torch.nn.init.normal_(module.weight,mean=0.0,std=0.02)
+            if module.bias is not None:
+                torch.nn.init.zeros_(module.bias)
+        elif isinstance(module,nn.Embedding):
+            torch.nn.init.normal_(module.weight,mean=0.0,std=0.02)
+
     def forward(self,idx, targets= None):
         B,T = idx.size()