Hugging Face 模型 · deepseek-ai ↗ · 2026-08-31
DeepSeek-V4-Flash-Vision-Exp
Model release Hugging Face 模型 · deepseek-ai Source language: Chinese
官方机构模型仓库创建于 2026-08-31。仓库创建时间不等于正式发布日期。任务类型:image-text-to-text
Full text
DeepSeek-V4-Flash-Vision-Exp
Introduction
We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.
Compared to DeepSeek-V4-Flash-0731, DeepSeek-V4-Flash-Vision-Exp achieves substantial improvements on its multimodal agent capabilities, while maintaining comparable performance on text-only agent tasks.
Benchmark DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-0731 Opus-4.8 Text Agent Capabilities Terminal Bench 2.1 83.9 82.7 85.0 NL2Repo 57.7 54.2 69.7 Cybergym 75.3 76.7 78.3 DeepSWE 59.3 54.4 58.0 Toolathlon-Verified 75.9 70.3 76.2 DSBench-Hard 63.6 59.6 71.7 AutomationBench (Public) 25.7 25.1 27.2 Multimodal Agent Capabilities ApexBench (Pass@1) 36.5 26.2† 39.4 Agents' Last Exam 27.3 25.2† 25.7 Chartography 64.3 - 65.0 ZeroBench (Pass@5) 35.0 - 34.0
Notes:
For the text agent benchmarks above, DeepSeek models are evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning effort level with temperature = 1.0, top_p = 0.95. † For ApexBench and Agents' Last Exam, DeepSeek-V4-Flash-0731 ignores the multimodal elements in the input.
Repository layout
This repository contains the tokenizer, prompt encoding reference, and a minimal PyTorch inference implementation for DeepSeek-V4 Flash Vision. The reference inference covers the vision encoder and aligner, DFlash attention, MoE, Hyper-Connections, and the DSpark forward path.
encoding/ and inference/ deliberately remain separate: prompt formatting does not depend on PyTorch, while inference imports the sibling encoding module with an explicit Python path. No symlinks are required.
The tokenizer files are regular files so that the repository can be uploaded to Hugging Face without relying on local filesystem symlinks. The large model shards are described by model.safetensors.index.json and are not duplicated inside the source checkout used to assemble this repository.
Prompt encoding
See encoding/README.md. Both OpenAI-style JSON content blocks and the compact path TXT notation are supported. The two examples under inference/examples/ encode to identical prompts and token IDs.
Minimal inference
See inference/README.md for dependency installation, checkpoint conversion, and TXT/JSON inference commands.
How to Run with vLLM
For example, the command below serves the model with vLLM on a single 4×GB300 node. See the vLLM recipe for detailed instructions and other hardware configurations.
How to Run with SGLang Enable DSpark with --speculative-algorithm DSPARK and do not set a separate --speculative-draft-model-path as the target and draft weights therefore come from the same checkpoint. See the SGLang cookbook for detailed instructions, benchmarks and other hardwares configurations.
License
This repository is licensed under the MIT License.