Downloads · 30 days
41
24% of all-time downloads
Qwen3.8-27B-Vision
immanuelpeter/Qwen3.8-27B-Vision
Qwen3.8-27B-Vision is a image feature extraction model from immanuelpeter. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This repository packages the Tower and learned merger from Qwen3.8-27B.
All-time downloads
172
Public
Parameters
461M
921 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors921 MB · 100%
At a glance
- Task
- Image Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_5_vision
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- 60a1bf93
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B Vision
This repository packages the Tower and learned merger from Qwen3.8-27B.
Contents
| File | Tensors | What it holds |
|---|---|---|
model.safetensors | 333 | Tower and learned merger, extracted from source shard 1 |
config.json | Vision-only Qwen3_5VisionConfig | |
preprocessor_config.json | Qwen image preprocessing configuration |
Qwen implements the learned merger inside Qwen3_5VisionModel, so this repository does
not need a separate Projector file.
Architecture
| Component | Details |
|---|---|
| Tower | 27 layers, 1152 hidden, 16 heads, 4304 intermediate, patch size 16 |
| Token compression | 2x2 spatial grouping |
| Learned merger | LayerNorm(1152), Linear(4608, 4608), GELU, Linear(4608, 5120) |
last_hidden_state contains the raw Tower tokens. pooler_output contains the merged
features at the language-model width.
Usage
See examples/inference.py for image feature extraction.
Validation
The release tests compare all 333 tensors with the pinned parent checkpoint using
torch.equal. Fixed-image Tower and merged outputs also match the parent implementation
bit-for-bit on CPU and in BF16 on an NVIDIA A100.
Reproduction
The export script
reads model.visual.* from shard 1 of Qwen/Qwen3.8-27B, removes the prefix, and writes
the original BF16 tensors. The script pins the parent revision.
Credits
Qwen released the Qwen3.8-27B weights and the native Transformers implementation.
License
Apache License 2.0, the same license as the source model.
- Task
- Image Feature Extraction
- Library
- transformers
- Type
- qwen3_5_vision
- License
- apache-2.0
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026