Merge pull request #1077 from mst272/main

update the code to use the module's __call__ (Issue #1055)

Author: subramen

llama/model.py

@@ -403,10 +403,10 @@ def forward(
             torch.Tensor: Output tensor after applying attention and feedforward layers.
 
         """
-        h = x + self.attention.forward(
+        h = x + self.attention(
             self.attention_norm(x), start_pos, freqs_cis, mask
         )
-        out = h + self.feed_forward.forward(self.ffn_norm(h))
+        out = h + self.feed_forward(self.ffn_norm(h))
         return out