A class that keeps all conversation history.

Computes and stores the average and current value

A class that keeps all conversation history.

Resizes images to the longest side 'target_length', as well as provides methods for resizing coordinates and boxes. Provides methods for

An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and values.

A structure for storing masks and their related data in batched format. Implements basic filtering and concatenation.

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

Multi-head Attention block with relative position embeddings.

Transformer blocks with support of window attention and residual propagation blocks

Collate examples for supervised fine-tuning.

Dataset for supervised fine-tuning.

Image to Patch Embedding.

Positional encoding using random spatial frequencies.

AutoTokenizer + Adaptation for MOD. A simple wrapper around AutoTokenizer to make instantiating an MOD-adapted tokenizer a bit easier. M

Multi-Query self attention. Using torch or triton attention implemetation enables user to also use additive bias.

Multi-head self attention. Using torch or triton attention implemetation enables user to also use additive bias.

This model should not be called directly, but is used in ONNX export. It combines the prompt encoder, mask decoder, and mask postprocessing o

Different separator style.

Different separator style.