--- license: apache-2.0 base_model: deepseek-ai/DeepSeek-V4-Flash-0731 tags: - multimodal - vision-language - deepseek - deepseek-v4 - screenshots - adapter - dgx-spark library_name: transformers pipeline_tag: image-text-to-text --- # DeepSeek-V4-Flash — Vision Encoder

Give your self-hosted DeepSeek eyes.
Official production tower + projector for DeepSeek-V4-Flash-0731.

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). ```text 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](https://github.com/FlyCockpit/DeepSeek-V4-Vision-2x-DGX-Sparks) --- ## Download ```bash hf download FlyCockpit/DeepSeek-V4-Flash-0731-vision \ --local-dir $HOME/dsv4-vision-assets ``` Or pull just the two weight files: ```bash 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](https://github.com/FlyCockpit/DeepSeek-V4-Vision-2x-DGX-Sparks/blob/main/docs/CAPABILITIES.md). --- ## 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** ```bash 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://: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