Downloads · 30 days
103
20% of all-time downloads
DeepSeek-V4-Flash-0731-vision
FlyCockpit/DeepSeek-V4-Flash-0731-vision
DeepSeek-V4-Flash-0731-vision is a image-text-to-text model from FlyCockpit. Use it for the image-text-to-text 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.
<p align="center" <strongGive your self-hosted DeepSeek eyes.</strong<br/ Official production <emtower + projector</em for <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731"DeepSeek-V4-Flash-0731</a. </p
All-time downloads
509
Public
Repo size
947 MB
Likes
11
Public
Repo makeup
Click a slice to open those files.
.safetensors907 MB · 92%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- d8efc7df
Try a prompt
Base models
Model card
From the Hugging Face model README
DeepSeek-V4-Flash — Vision Encoder
<p align="center"> <strong>Give your self-hosted DeepSeek eyes.</strong><br/> Official production <em>tower + projector</em> for <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731">DeepSeek-V4-Flash-0731</a>. </p>This repo is only the vision stack (about 900 MB total). The language model itself is still the upstream 0731 FP8 checkpoint (about 167 GB).
image → DeepEncoderV2 tower → projector → splice at token 129279
→ DeepSeek-V4-Flash-0731
Serve it on 2× DGX Spark:
→ FlyCockpit/DeepSeek-V4-Vision-2x-DGX-Sparks
Download
hf download FlyCockpit/DeepSeek-V4-Flash-0731-vision \
--local-dir $HOME/dsv4-vision-assets
Or pull just the two weight files:
hf download FlyCockpit/DeepSeek-V4-Flash-0731-vision \
adapter/latest.pt \
tower/deepencoder_v2_tower.safetensors \
--local-dir $HOME/dsv4-vision-assets
Files
| path | what | size | md5 |
|---|---|---|---|
adapter/latest.pt | use this — final projector | 40 MB | d9b3b3bda8f790ecf7cd5a98e6fb93a5 |
adapter/merged-004800-5af0c5.pt | same bytes (named by step) | 40 MB | d9b3b3bda8f790ecf7cd5a98e6fb93a5 |
tower/deepencoder_v2_tower.safetensors | frozen image tower | 865 MB | 2d5dba626d816cc367d28b32e744830e |
config.json | release metadata | tiny | — |
Final training step: 4800. Layout: tiles=2 (257 / 769 / 1281 image tokens).
What it's for
| Strength | Notes |
|---|---|
| UI / screenshot understanding | Primary target |
| Documents & on-screen text | Strong |
| Everyday photos | Decent |
| Click agents on arbitrary real UIs | Not claimed — see below |
Synthetic GUI coordinate probes pass; real-page computer-use does not transfer cleanly yet. Full write-up lives in the playbook's capabilities doc.
Compatibility (important)
This encoder maps into 0731's embedding space.
| base weights | works? |
|---|---|
deepseek-ai/DeepSeek-V4-Flash-0731 | yes |
| older Flash / DSpark / NVIDIA NVFP4 of the old line | no |
Precision (FP8 vs a future 0731-matched quant) is fine. Different training lineage is not.
Serve
Use the open playbook (Mia-style, worker-first TP=2):
https://github.com/FlyCockpit/DeepSeek-V4-Vision-2x-DGX-Sparks
git clone https://github.com/FlyCockpit/DeepSeek-V4-Vision-2x-DGX-Sparks.git
cd DeepSeek-V4-Vision-2x-DGX-Sparks
cp .env.vision.example .env.vision # set fabric IPs
bash scripts/download-assets.sh
bash scripts/build-image.sh
bash scripts/start-vision.sh # run on head
API: http://<head>:8899/v1 · model id: deepseek-v4-flash-0731-vision
License
- Adapter packaging in this repo: Apache-2.0
- DeepEncoderV2 tower & DeepSeek-V4-Flash-0731 backbone: upstream terms apply
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026