r""" Returns: `dict` of attention processors: A dictionary containing all attention processors used in the model with

Unified chat function Args: image: use for batch_size=1 vqa, It is not recommended to continue to use this parameter

Sets the attention processor to use [feed forward chunking](https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers).

Input shape: Batch x Time x Channel

Args: hidden_states (`torch.FloatTensor`): Input to the layer of shape `(batch, seq_len, embed_dim)`.

r""" Args: inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`): Optionally,

r""" Returns:

r""" Args: hidden_states (`torch.FloatTensor` of shape `(batch_size, seq_len, embed_dim)`): Hidden states to be fe

r""" Forward pass of the Whisper encoder. Args: input_features (`torch.FloatTensor` of shape `(batch_size, feature_size,

audio: Tensor([num_channels, num_samples])

The [`FluxTransformer2DModel`] forward method. Args: hidden_states (`torch.FloatTensor` of shape `(batch size, channel,

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for position (index) of the start of the la

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

Implements the multihead softmax attention. Arguments --------- qkv: The tensor containing the query, key, and value. (B,