Print information about the VQA annotation file. :return:

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding

This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding

Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str,

Apply rotary embedding to the first rotary_dim of the iput Arguments: t (tensor(batch_size, seq_len, n_head, head_dim)): the input

Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str,

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

Build a module from config dict when it is a class configuration, or call a function from config dict when it is a function configuration. Ex

Overrides `generate` function to be able to use the model as a conditional generator. Args: pixel_values (`torch.FloatTe

Normalize the str to lower case and make them float numbers if possible.

Normalize the str to lower case and make them float numbers if possible.

Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.

Make causal mask used for bi-directional self-attention.

Tokenize a list of strings.