To celebrate, we are shipping with Meta day-0 support in transformers, llama.cpp, vLLM, Inference Endpoints, and other libraries. We built a few cool things and explain our findings in this blog.

Scores are reported as published. Bold indicates the best result among the compared models; ↓ indicates lower is better.

In addition to the main VLM, there’s also a speculative decoding drafter implemented on DFlash. Usage of this module is optional, and it can provide much faster generation in exchange for some memory cost. We found this drafter to be particularly well suited to structured content generation such as coding.

Muse Glimmer uses one image encoder to handle both images and videos. Unlike the relatively small vision encoders used in other VLMs, this is a sizable 2B ViT-like model designed after the Perception Encoder architecture. Perception Encoder was previously introduced by Meta as a backbone for various downstream spatial and multimodal tasks.
The encoder patchifies images to a shape of 2 frames x 3 channels x 14 x 14, and passes them through a linear layer for projection. An interpolated absolute position embedding from a learned position table is then added to these embeddings. These are then sent to the vision tower which consist of 50 layers and GELU MLPs. Similar to the language model, the attention pattern consists of three window attention layers followed by one full attention layer. Inside the attention layers, 2D RoPE is applied to the queries and keys.

After transformer, pixel shuffle concatenates 2x2 groups of neighboring spatial tokens which reduces the number of image tokens 4x without discarding their channels.

Source link