remove spurious cast, gets compiled away anyway but it's confusing people

nanochat/gpt.py

@@ -41,12 +41,10 @@ def norm(x):
 def apply_rotary_emb(x, cos, sin):
     assert x.ndim == 4  # multihead attention
     d = x.shape[3] // 2
-    x1, x2 = x[..., :d], x[..., d:] # split up last time into two halves
+    x1, x2 = x[..., :d], x[..., d:] # split up last dim into two halves
     y1 = x1 * cos + x2 * sin # rotate pairs of dims
     y2 = x1 * (-sin) + x2 * cos
-    out = torch.cat([y1, y2], 3) # re-assemble
-    out = out.to(x.dtype) # ensure input/output dtypes match
-    return out
+    return torch.cat([y1, y2], 3)
 
 class CausalSelfAttention(nn.Module):
     def __init__(self, config, layer_idx):