DeepSeek-ViT

This repository packages DeepSeek-ViT and the two-layer MLP projector from DeepSeek-V4.1-Flash.

File	Tensors	What it holds
`model.safetensors`	259	DeepSeek-ViT Tower, extracted from source shard 1
`projector.safetensors`	4	Two-layer MLP Aligner
`config.json`		Vision-only `DeepSeekV41ViT`
`vision.py`		Standalone ViT and Aligner used by `examples/inference.py`

This repository does not include Transformers modeling files or a preprocessor config. AutoModel.from_pretrained will not work.

Architecture

Component	Details
Tower	32 layers, 1024 hidden, 16 heads, 2816 intermediate, patch size 14, 2D-RoPE
Token compression	3x3 unfold / pixel-unshuffle with padding
Aligner	`Linear(9216, 5120)`, GELU, `Linear(5120, 5120)`, both with bias

Usage

See examples/inference.py for image feature extraction. AutoModel.from_pretrained will not load this repository. The example uses vision.py in this repo.

Validation

The parity script compares all 259 Tower tensors and 4 Aligner tensors with the pinned parent checkpoint using torch.equal.

Reproduction

The export script reads vision.* and aligner.* from shard 1 of deepseek-ai/DeepSeek-V4.1-Flash, removes the prefixes, and writes the original BF16 tensors.

Credits

DeepSeek released the DeepSeek-V4.1-Flash weights. DeepSeek-ViT is described in DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression.

License

MIT License, the same license as the source model.

Downloads last month: 36

Safetensors

Model size

0.4B params

Tensor type

BF16

Inference Providers NEW

Image Feature Extraction

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for immanuelpeter/DeepSeek-ViT

Base model

deepseek-ai/DeepSeek-V4.1-Flash

Finetuned

(26)

this model

Collection including immanuelpeter/DeepSeek-ViT

Vision Heads

Collection

Vision heads extracted from MLLMs • 13 items • Updated 14 days ago

immanuelpeter
/

DeepSeek-ViT