Disable tqdm progress bar.

Disable tqdm progress bar.

Disable propagation of the library log outputs. Note that log propagation is disabled by default.

Disable propagation of the library log outputs. Note that log propagation is disabled by default.

Disable the redundant torch default initialization to accelerate model creation.

r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).

r""" Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).

`torch.dtype`: The dtype of the module (assuming that all the module parameters have the same dtype).

`torch.dtype`: The dtype of the module (assuming that all the module parameters have the same dtype).

Enable the default handler of the HuggingFace muse' root logger.

Enable the default handler of the HuggingFace muse' root logger.

Enable explicit formatting for every HuggingFace muse' logger. The explicit formatter is as follows: ``` [LEVELNAME|FILENAME|LINE NUM

Enable explicit formatting for every HuggingFace muse' logger. The explicit formatter is as follows: ``` [LEVELNAME|FILENAME|LINE NUM

Helper function for reproducible behavior during distributed training. See - https://pytorch.org/docs/stable/notes/randomness.html for pytorc

Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or *checkpoint activations*

Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or *checkpoint activations*

r""" Enable npu flash attention from torch_npu

r""" Enable npu flash attention from torch_npu

Enable tqdm progress bar.

Enable tqdm progress bar.

Enable propagation of the library log outputs. Please disable the HuggingFace muse' default handler to prevent double logging if the root log

Enable propagation of the library log outputs. Please disable the HuggingFace muse' default handler to prevent double logging if the root log

r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, yo

r""" Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/). When this option is enabled, yo

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

Forward pass to extract features from the penultimate layer. Args: x: Input image tensor (pixel values). Return

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""" Returns: Examples: ```python >>> from transformers import AutoTokenizer, SiglipTextModel >>> model = S

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

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

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

Forward pass to extract features from the penultimate layer. Args: x: Input image tensor (pixel values). Return

Fix bfloat16 support for nearest neighbor interpolation.