Update chatNT.py

chatNT.py

@@ -1188,11 +1188,6 @@ class RotaryEmbeddingBis(torch.nn.Module):
             heads[..., heads.shape[-1] // 2 :],
         )
 
-        print("x_first device : ", x_first.device)
-        print("cos device : ", cos.device)
-        print("x_second device : ", x_second.device)
-        print("sin device : ", sin.device)
-
         first_part = x_first * cos - x_second * sin
         second_part = x_second * cos + x_first * sin
 
@@ -1201,13 +1196,11 @@ class RotaryEmbeddingBis(torch.nn.Module):
     def _compute_cos_sin_tables(
         self, x: torch.Tensor, inv_freq: torch.Tensor, seq_dimension: int = 2
     ) -> tuple[torch.Tensor, torch.Tensor]:
-        print("x device : ", x.device)
         seq_len = x.shape[seq_dimension]
         # Reset the tables if the sequence length has changed,
         # or if we're on a new device (possibly due to tracing for instance)
         self._seq_len_cached = seq_len
         t = torch.arange(x.shape[seq_dimension], device=x.device).type_as(inv_freq)
-        print("t device : ", t.device)
         # freqs = torch.outer(t, inv_freq)
         freqs = torch.einsum("i, j -> ij", t, inv_freq)
 
@@ -1235,8 +1228,6 @@ class RotaryEmbeddingBis(torch.nn.Module):
                 updated_base ** (torch.arange(0, self.dim, 2, device=q.device).float() / self.dim)
             )
 
-        print("q device : ", q.device)
-        print("inv_freq device : ", inv_freq.device)
         self._cos_cached, self._sin_cached = self._compute_cos_sin_tables(
             q,
             inv_freq,