immanuelpeter's picture
Link the card to its export and parity check in vision-tower-bench
41247dd verified
|
Raw History Blame Contribute Delete
2.11 kB
metadata
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
pipeline_tag: image-feature-extraction
library_name: pytorch
tags:
  - vision
  - feature-extraction
  - nemotron
base_model:
  - nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16

C-RADIOv4-H-3.5-Bolt

This repository packages the C-RADIOv4-H Tower and Projector from Nemotron 3.5 Bolt.

Contents

File Tensors What it holds
model.safetensors 391 RADIO Tower from Bolt vision_model.*, including summary_idxs
projector.safetensors 3 Bolt mlp1 Projector
config.json Source and code pins and widths
vision.py Loader used by examples/inference.py

Architecture

Component Details
Tower C-RADIOv4-H, 32 layers, 1280 hidden, patch size 16, ten prefix tokens
Token compression InternVL v2 2x2 pixel shuffle, scale 0.5, no learned parameters
Projector (mlp1) RMSNorm(5120), Linear(5120, 20480) no bias, SquaredReLU, Linear(20480, 4096) no bias

At 448 the bench reports 784 Tower tokens of width 1280, 196 merged tokens of width 5120, and 196 projected tokens of width 4096.

Usage

See examples/inference.py for image feature extraction.

Validation

The parity check compares every exported tensor with the pinned parent using torch.equal, then checks all stages against the parent's own RadioModel and VisionProjector code.

Reproduction

The export script reads vision_model.* and mlp1.* from the pinned parent and writes the original BF16 tensors.

Credits

NVIDIA released Nemotron 3.5 Bolt and C-RADIOv4-H.

License

OpenMDW-1.1, the license from the source model card.