(original_tensor, target_len)
| 13 | return x.to(position.dtype) |
| 14 | |
| 15 | def pad_freqs(original_tensor, target_len): |
| 16 | seq_len, s1, s2 = original_tensor.shape |
| 17 | pad_size = target_len - seq_len |
| 18 | padding_tensor = torch.ones( |
| 19 | pad_size, |
| 20 | s1, |
| 21 | s2, |
| 22 | dtype=original_tensor.dtype, |
| 23 | device=original_tensor.device) |
| 24 | padded_tensor = torch.cat([original_tensor, padding_tensor], dim=0) |
| 25 | return padded_tensor |
| 26 | |
| 27 | def rope_apply(x, freqs, num_heads): |
| 28 | x = rearrange(x, "b s (n d) -> b s n d", n=num_heads) |