Fix syntax error in gated_deltaproduct.py and add matplotlib dependency

requirements.txt

@@ -18,3 +18,4 @@ python-dateutil>=2.8.0
 pytz>=2021.1
 PyYAML>=5.4.1
 flash-linear-attention @ git+https://github.com/fla-org/flash-linear-attention@main
+matplotlib>=3.5.0

src/models/gated_deltaproduct/gated_deltaproduct.py

@@ -74,11 +74,9 @@ class GatedDeltaProduct(nn.Module):
         # Consistency check: Ensure expand_v produces integer values
         if not math.isclose(self.num_v_heads * self.head_dim * expand_v, self.value_dim, rel_tol=1e-5):
             raise ValueError(
-                f"expand_v={expand_v} does not produce an integer value when multiplied by key_dim={self.key_dim}. "(
-                    f"Resulting value_dim would be "
-                    f"{self.num_v_heads * self.head_dim * expand_v}, "
-                    "which is invalid for nn.Linear."
-                )
+                f"expand_v={expand_v} does not produce an integer value when multiplied by key_dim={self.key_dim}. "
+                f"Resulting value_dim would be {self.num_v_heads * self.head_dim * expand_v}, "
+                "which is invalid for nn.Linear."
             )
         if self.num_v_heads > self.num_heads and self.num_v_heads % self.num_heads != 0:
             raise ValueError(f"num_v_heads={self.num_v_heads} must be divisible by num_heads={self.num_heads}.")