A class that keeps all conversation history.

Rescales the input PIL.Image to the given 'size'. 'size' will be the size of the smaller edge. For example, if height > width, then image wil

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Fake file-like stream object that redirects writes to a logger instance.

Converts a PIL.Image (RGB) or numpy.ndarray (H x W x C) in the range [0, 255] to a torch.FloatTensor of shape (C x H x W) in the range [0.0, 1.0]

Convolutional 2D subsampling (to 1/4 length). Args: idim (int): Input dimension. odim (int): Output dimension. dropout_ra

Convolutional 2D subsampling (to 1/4 length). Args: idim (int): Input dimension. odim (int): Output dimension. dropout_ra

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Collate examples for supervised fine-tuning.

Vision Transformer with support for patch or hybrid CNN input stage

Implement the scaled dot product attention with softmax. Arguments --------- softmax_scale: The temperature to use for the softmax att

Multi-headed attention from 'Attention Is All You Need' paper

r""" This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to instantiate a vision encoder accordi

Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a [`InternEncoderLayer`]. Args:

E2E module. Args: idim (int): dimension of inputs odim (int): dimension of outputs args (namespace): argument Namespace c

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

Dataset for supervised fine-tuning.

r""" Sampler that samples indices in a way that groups together features of the dataset of roughly the same length while keeping a bit of rand

This implementation fine-tunes 20 LoRA modules based on the InternVL-Chat-V1-5 model. The fine-tuned LoRA modules are then merged with the In

Multi-Head Attention layer. :param int n_head: the number of head s :param int n_feat: the number of features :param float dropout_rate:

Multi-Head Attention layer. :param int n_head: the number of head s :param int n_feat: the number of features :param float dropout_rate:

Multi-input multi-output torch.nn.Sequential.

Multi-input multi-output torch.nn.Sequential.

https://arxiv.org/abs/2212.00794

Image to Patch Embedding

Relative positional encoding module. See : Appendix B in https://arxiv.org/abs/1901.02860 Args: d_model (int): Embedding dimension.