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

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

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

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

rewrite forward of QwenModel.

rewrite forward of QwenModel.

Input shape: Batch x Time x Channel

Input shape: Batch x Time x Channel

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

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

r""" Returns:

r""" Returns: Examples: ```python >>> from transformers import AutoTokenizer, CLIPTextModel >>> model = CLI

r""" Returns:

r""" Returns: Examples: ```python >>> from PIL import Image >>> import requests >>> from transformer

r""" Returns: Examples: ```python >>> from PIL import Image >>> import requests >>> from transformer

r""" Returns: Examples: ```python >>> from transformers import AutoTokenizer, CLIPTextModelWithProjection >

r""" Returns: Examples: ```python >>> from PIL import Image >>> import requests >>> from transformer

qkv: (batch, seqlen, 3, nheads, headdim) bias: optional, shape broadcastible to (batch, nheads, seqlen, seqlen).

q: (batch, seqlen_q, nheads, headdim) kv: (batch, seqlen_k, 2, nheads, headdim) bias: optional, shape broadcastib

q: (batch_size, seqlen_q, nheads, headdim) k, v: (batch_size, seqlen_k, nheads, headdim) bias: optional, shape br

r""" Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model configuration.

Wraps original generate to enable PrefixLM attention.