Method to obtain re-parameterized kernel and bias. Reference: https://github.com/DingXiaoH/RepLKNet-pytorch Returns: Tupl

Make dataset and collator for supervised fine-tuning.

Make dataset and collator for supervised fine-tuning.

Given a list of sources, each is a conversation list. This transform: 1. Add signal '### ' at the beginning each sentence, with end signal '\

Given a list of sources, each is a conversation list. This transform: 1. Add signal '### ' at the beginning each sentence, with end signal '\

Resize and pad an image to a target resolution while maintaining aspect ratio. Args: image (PIL.Image.Image): The input image.

Collects the state dict and dump to disk.

Collects the state dict and dump to disk.

Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.

Resize tokenizer and embedding. Note: This is the unoptimized version that may make your embedding size not be divisible by 64.

Split a list of indices into `chunks` chunks of roughly equal lengths.

Unpads a PyTorch tensor of a padded and resized image. Args: tensor (torch.Tensor): The image tensor, assumed to be in CxHxW format.

Check whether the text violates OpenAI moderation API.

Construct a Squeeze and Excite Module. Args: in_channels: Number of input channels. rd_ratio: Input channel reduction

Construct a MobileOneBlock module. Args: in_channels: Number of channels in the input. out_channels: Number of channe

Construct a ReparamLargeKernelConv module. Args: in_channels: Number of input channels. out_channels: Number of outpu

Build patch embedding layer. Args: patch_size: Patch size for embedding computation. stride: Stride for convolutional

Build RepMixer Module. Args: dim: Input feature map dimension. :math:`C_{in}` from an expected input of size :math:`(B, C_{in}, H

Build convolutional FFN module. Args: in_channels: Number of input channels. hidden_channels: Number of channels afte

Build reparameterizable conditional positional encoding Args: in_channels: Number of input channels. embed_dim: Numbe

Build RepMixer Block. Args: dim: Number of embedding dimensions. kernel_size: Kernel size for repmixer. Default: 3

Build Attention Block. Args: dim: Number of embedding dimensions. mlp_ratio: MLP expansion ratio. Default: 4.0