# tensorplay.nn.attention.create_mask

Source: https://www.tensorplay.cn/docs/generated/tensorplay.nn.attention.create_mask.html

```python
tensorplay.nn.attention.create_mask(mod_fn: _score_mod_signature | _mask_mod_signature, B: int | None, H: int | None, Q_LEN: int, KV_LEN: int, device: DeviceLikeType | None = None) → Tensor
```

This function creates a mask tensor from a mod_fn function.

Parameters:

- mod_fn (Union[_score_mod_signature, _mask_mod_signature]) – Function to modify attention scores.

- B ([int](https://docs.python.org/3/builtins/functions.html#int)) – Batch size.

- H ([int](https://docs.python.org/3/builtins/functions.html#int)) – Number of query heads.

- Q_LEN ([int](https://docs.python.org/3/builtins/functions.html#int)) – Sequence length of query.

- KV_LEN ([int](https://docs.python.org/3/builtins/functions.html#int)) – Sequence length of key/value.

- device ([str](https://docs.python.org/3/builtins/stdtypes.html#str)) – Device to run the mask creation on.

Returns:

A mask tensor with shape (B, H, M, N).

Return type:

mask ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor))