Save the model configuration to the ``config_path``. The final configuration will be sorted before saving for better readability. Args:

Save the model configuration to the ``config_path``. The final configuration will be sorted before saving for better readability. Args:

Save model weights into specified directory.

Save model weights into specified directory.

Calculates the image embeddings for the provided image, allowing masks to be predicted with the 'predict' method. Args:

Set up and return the argument parser.

Returns sinusoids for positional embedding

Returns sinusoids for positional embedding

Euler flow-matching update: x_new = x + f * (sigma_next - sigma).

Apply top-k sampling to logits. Args: logits: The logits from the model's output. top_k: Sample from the top k logits.

Splits the loaded dataset into train/validation/test sets.

Uploads the model to Hugging Face hub. Args: path (str): Local path to the model. upload_repo (str): Name of the HF repo to

Partition into non-overlapping windows with padding if needed. Args: x (mx.array): input tokens with [B, H, W, C]. window_siz

Window unpartition into original sequences and removing padding. Args: windows (mx.array): input tokens with [B * num_windows, window

Predict masks given image and prompt embeddings. Args: image_embeddings (mx.array): the embeddings from the image encode

Args: image_embedding (mx.array): image to attend to. Should be shape B x h x w x embedding_dim for any h and w.

Predicts masks end-to-end from provided images and prompts. If prompts are not known in advance, using SamPredictor is recomm

Embeds different types of prompts, returning both sparse and dense embeddings. Args: points (tuple(mx.array, mx.

Generate positional encoding for a grid of the specified size.

Compute binned relative position bias