Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek VL-7B-Chat

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

4K tokens

Max output length

No data

Model type

多模态大模型

Release date

2024-03-11

Model file size

14GB

MoE architecture

Total params / Active params

70.0B / N/A

Knowledge cutoff

No data

DeepSeek VL-7B-Chat

Open source & experience

Code license

MIT License

Weights license

DEEPSEEK LICENSE AGREEMENT- 免费商用授权

GitHub repo

https://github.com/deepseek-ai/DeepSeek-VL

Hugging Face

https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat

Live demo

No live demo

DeepSeek VL-7B-Chat

Official resources

Paper

DeepSeek-VL: Towards Real-World Vision-Language Understanding

DataLearnerAI blog

No blog post yet

DeepSeek VL-7B-Chat

API details

API speed

No data

No public API pricing yet.

DeepSeek VL-7B-Chat

Benchmark Results

No benchmark data to show.

DeepSeek VL-7B-Chat

Publisher

DeepSeek-AI

View publisher details

DeepSeek Vision-Language-7B-Chat

Model Overview

Deepseek Vision-Language-7B-Chat简称Deepseek VL-7B-Chat，是DeepSeekAI开源的一个多模态大模型，可以理解图片。最高支持1024*1024分辨率图像的输入，是目前已知的支持最高图像解析度的多模态大模型之一。

Deepseek VL-7B-Chat是基于DeepSeek-LLM-7B-Chat版本进行训练的，是其中的指令微调过的版本。可以更加好的应用在聊天场景。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送