HuggingFace镜像/deepseek-vl-7b-base
模型介绍文件和版本分析
下载使用量0

1. 引言

介绍DeepSeek-VL，一款开源的视觉-语言（VL）模型，专为现实世界的视觉与语言理解应用设计。DeepSeek-VL具备通用的多模态理解能力，能够处理逻辑图表、网页、公式识别、科学文献、自然图像以及在复杂场景中的具身智能。

DeepSeek-VL：迈向现实世界的视觉-语言理解

GitHub 仓库

Haoyu Lu*，Wen Liu*，Bo Zhang**，Bingxuan Wang，Kai Dong，Bo Liu，Jingxiang Sun，Tongzheng Ren，Zhuoshu Li，Hao Yang，Yaofeng Sun，Chengqi Deng，Hanwei Xu，Zhenda Xie，Chong Ruan (*同等贡献，**项目负责人)

2. 模型概述

DeepSeek-VL-7b-base 使用 SigLIP-L 和 SAM-B 作为混合视觉编码器，支持 1024 x 1024 图像输入，并基于在近 2T 文本标记语料库上训练的 DeepSeek-LLM-7b-base 构建而成。整个 DeepSeek-VL-7b-base 模型最终在大约 400B 视觉-语言标记上进行训练。

3. 快速入门

安装

在 Python >= 3.8 环境基础上，通过运行以下命令安装必要的依赖项：

git clone https://github.com/deepseek-ai/DeepSeek-VL
cd DeepSeek-VL

pip install -e .

简单推理示例

import torch
from transformers import AutoModelForCausalLM

from deepseek_vl.models import VLChatProcessor, MultiModalityCausalLM
from deepseek_vl.utils.io import load_pil_images


# specify the path to the model
model_path = "deepseek-ai/deepseek-vl-7b-base"
vl_chat_processor: VLChatProcessor = VLChatProcessor.from_pretrained(model_path)
tokenizer = vl_chat_processor.tokenizer

vl_gpt: MultiModalityCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
vl_gpt = vl_gpt.to(torch.bfloat16).cuda().eval()

conversation = [
    {
        "role": "User",
        "content": "<image_placeholder>Describe each stage of this image.",
        "images": ["./images/training_pipelines.png"]
    },
    {
        "role": "Assistant",
        "content": ""
    }
]

# load images and prepare for inputs
pil_images = load_pil_images(conversation)
prepare_inputs = vl_chat_processor(
    conversations=conversation,
    images=pil_images,
    force_batchify=True
).to(vl_gpt.device)

# run image encoder to get the image embeddings
inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)

# run the model to get the response
outputs = vl_gpt.language_model.generate(
    inputs_embeds=inputs_embeds,
    attention_mask=prepare_inputs.attention_mask,
    pad_token_id=tokenizer.eos_token_id,
    bos_token_id=tokenizer.bos_token_id,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=512,
    do_sample=False,
    use_cache=True
)

answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
print(f"{prepare_inputs['sft_format'][0]}", answer)

命令行聊天界面


python cli_chat.py --model_path "deepseek-ai/deepseek-vl-7b-base"

# or local path
python cli_chat.py --model_path "local model path"

4. 许可

该代码仓库遵循 MIT 许可证 进行授权。使用 DeepSeek-VL 基础/聊天模型需遵守 DeepSeek 模型许可证。DeepSeek-VL 系列产品（包括基础版和聊天版）均支持商业用途。

5. 引用

@misc{lu2024deepseekvl,
      title={DeepSeek-VL: Towards Real-World Vision-Language Understanding}, 
      author={Haoyu Lu and Wen Liu and Bo Zhang and Bingxuan Wang and Kai Dong and Bo Liu and Jingxiang Sun and Tongzheng Ren and Zhuoshu Li and Yaofeng Sun and Chengqi Deng and Hanwei Xu and Zhenda Xie and Chong Ruan},
      year={2024},
      eprint={2403.05525},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

6. 联系我们

如有任何疑问，请发起一个议题或通过 service@deepseek.com 与我们联系。