nemo_automodel.components.models.deepseek_v41.vision

Reuse the unchanged DeepSeek vision encoder with the V4.1 nested config.

Module Contents

Classes

Name	Description
`DeepseekV41VisionAligner`	The released padded spatial merger and GELU projection into text width.
`DeepseekV41VisionTransformer`	The released full-attention 2D-RoPE ViT, configured by nested V4.1 fields.

Functions

Name	Description
`_vision_config`	Translate the typed V4.1 config into the existing vision implementation’s config.

API

class nemo_automodel.components.models.deepseek_v41.vision.DeepseekV41VisionAligner(
    config: nemo_automodel.components.models.deepseek_v41.config.DeepseekV41Config
)

Bases: DeepseekV4VisionAligner

The released padded spatial merger and GELU projection into text width.

Parameters:

config

DeepseekV41Config

Top-level V4.1 configuration containing vision and text widths.

class nemo_automodel.components.models.deepseek_v41.vision.DeepseekV41VisionTransformer(
    config: nemo_automodel.components.models.deepseek_v41.config.DeepseekV41Config
)

Bases: DeepseekV4VisionTransformer

The released full-attention 2D-RoPE ViT, configured by nested V4.1 fields.

Parameters:

config

DeepseekV41Config

Top-level V4.1 configuration containing the vision dimensions.

nemo_automodel.components.models.deepseek_v41.vision._vision_config(
    config: nemo_automodel.components.models.deepseek_v41.config.DeepseekV41Config
) -> nemo_automodel.components.models.deepseek_v4.config.DeepseekV4Config

Translate the typed V4.1 config into the existing vision implementation’s config.