介绍DeepSeek-VL,这是一个开源的视觉-语言(VL)模型,专为现实世界的视觉与语言理解应用而设计。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、自然图像以及复杂场景中的具身智能。
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,**项目主导)

DeepSeek-VL-1.3b-chat 是一个迷你型视觉-语言模型。它使用 SigLIP-L 作为视觉编码器,支持 384 x 384 图像输入,并基于 DeepSeek-LLM-1.3b-base 构建而成,后者在约 5000 亿个文本标记的语料库上进行了训练。整个 DeepSeek-VL-1.3b-base 模型最终在约 4000 亿个视觉-语言标记上进行了训练。DeepSeek-VL-1.3b-chat 是基于 DeepSeek-VL-1.3b-base 的指令版本。
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 .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-1.3b-chat"
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)
python cli_chat.py --model_path "deepseek-ai/deepseek-vl-1.3b-chat"
# or local path
python cli_chat.py --model_path "local model path"
本代码仓库遵循 MIT 许可证 进行授权。DeepSeek-VL 基础/聊天模型的使用需遵守 DeepSeek 模型许可。DeepSeek-VL 系列(包括基础和聊天模型)均支持商业用途。
@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}
}如果您有任何问题,请创建一个议题或通过 service@deepseek.com 与我们联系。