A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1

• URL: http://arxiv.org/abs/2505.00025v1
• Date: Fri, 25 Apr 2025 14:28:29 GMT
• Title: A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1
• Authors: Mingda Zhang, Jianglong Qin,
• Abstract summary: This paper proposes an efficient lightweight medical vertical large model architecture method.<n>At the knowledge acquisition level, a knowledge transfer pipeline is designed from the fine-tuned DeepSeek-R1-Distill-70B teacher model to the DeepSeek-R1-Distill-7B student model.<n>At the model compression level, compression techniques including 4-bit weight quantization are implemented while preserving the core representation for medical reasoning.
• Score: 6.589206192038366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, despite foundation models like DeepSeek-R1 and ChatGPT demonstrating significant capabilities in general tasks, professional knowledge barriers, computational resource requirements, and deployment environment limitations have severely hindered their application in actual medical scenarios. Addressing these challenges, this paper proposes an efficient lightweight medical vertical large language model architecture method, systematically solving the lightweight problem of medical large models from three dimensions: knowledge acquisition, model compression, and computational optimization. At the knowledge acquisition level, a knowledge transfer pipeline is designed from the fine-tuned DeepSeek-R1-Distill-70B teacher model to the DeepSeek-R1-Distill-7B student model, and Low-Rank Adaptation (LoRA) technology is adopted to precisely adjust key attention layers. At the model compression level, compression techniques including 4-bit weight quantization are implemented while preserving the core representation ability for medical reasoning. At the computational optimization level, inference optimization techniques such as Flash Attention acceleration and continuous batching are integrated, and a professional prompt template system is constructed to adapt to different types of medical problems. Experimental results on medical question-answering datasets show that the method proposed in this paper maintains professional accuracy while reducing memory consumption by 64.7\% and inference latency by 12.4\%, providing an effective solution for the application of medical large models in resource-constrained environments such as edge computing devices.

Related papers

• Knowledge Distillation: Enhancing Neural Network Compression with Integrated Gradients [0.0]
  This paper proposes a machine learning framework that augments Knowledge Distillation (KD) with Integrated Gradients (IG)<n>We introduce a novel data augmentation strategy where IG maps, precomputed from a teacher model, are overlaid onto training images to guide a compact student model toward critical feature representations.<n>Experiments on CIFAR-10 demonstrate the efficacy of our method: a student model, compressed 4.1-fold from the MobileNet-V2 teacher, achieves 92.5% classification accuracy, surpassing the baseline student's 91.4% and traditional KD approaches, while reducing inference latency from 140 ms to 13 ms--a tenfold
  arXiv  Detail & Related papers  (2025-03-17T10:07:50Z)
• Pathology Image Compression with Pre-trained Autoencoders [52.208181380986524]
  Whole Slide Images in digital histopathology pose significant storage, transmission, and computational efficiency challenges. Standard compression methods, such as JPEG, reduce file sizes but fail to preserve fine-grained phenotypic details critical for downstream tasks. In this work, we repurpose autoencoders (AEs) designed for Latent Diffusion Models as an efficient learned compression framework for pathology images.
  arXiv  Detail & Related papers  (2025-03-14T17:01:17Z)
• Structured Model Pruning for Efficient Inference in Computational Pathology [2.9687381456164004]
  We develop a methodology for pruning the widely used U-Net-style architectures in biomedical imaging. We empirically demonstrate that pruning can compress models by at least 70% with a negligible drop in performance.
  arXiv  Detail & Related papers  (2024-04-12T22:05:01Z)
• Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation [113.5002649181103]
  Training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
  arXiv  Detail & Related papers  (2024-03-12T18:12:02Z)
• Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference [13.403419873964422]
  We highlight the excess operational complexity in a suboptimally configured ML model from prior work. Our results show a compression rate of 1148x with minimal loss in quality. We consider avenues for future research in streamlining for clinical researchers to develop models quicker and better suited for real-world use.
  arXiv  Detail & Related papers  (2023-09-10T17:34:14Z)
• An Evaluation of Lightweight Deep Learning Techniques in Medical Imaging for High Precision COVID-19 Diagnostics [0.0]
  Decision support systems relax the challenges inherent to the physical examination of images. Most deep learning algorithms utilised approaches are not amenable to implementation on resource-constrained devices. This paper presents the development and evaluation of the performance of lightweight deep learning technique for the detection of COVID-19 using the MobileNetV2 model.
  arXiv  Detail & Related papers  (2023-05-30T13:14:03Z)
• Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey [53.258091735278875]
  This survey covers studies of design automation techniques for deep learning models targeting edge computing. It offers an overview and comparison of key metrics that are used commonly to quantify the proficiency of models in terms of effectiveness, lightness, and computational costs. The survey proceeds to cover three categories of the state-of-the-art of deep model design automation techniques.
  arXiv  Detail & Related papers  (2022-08-22T12:12:43Z)
• Ultrasound Signal Processing: From Models to Deep Learning [64.56774869055826]
  Medical ultrasound imaging relies heavily on high-quality signal processing to provide reliable and interpretable image reconstructions. Deep learning based methods, which are optimized in a data-driven fashion, have gained popularity. A relatively new paradigm combines the power of the two: leveraging data-driven deep learning, as well as exploiting domain knowledge.
  arXiv  Detail & Related papers  (2022-04-09T13:04:36Z)
• SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images [62.60956024215873]
  Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. This study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin diseases classification.
  arXiv  Detail & Related papers  (2022-03-22T06:54:29Z)
• Demystifying Deep Learning Models for Retinal OCT Disease Classification using Explainable AI [0.6117371161379209]
  The adoption of various deep learning techniques is quite common as well as effective, and its statement is equally true when it comes to implementing it into the retina Optical Coherence Tomography sector. These techniques have the black box characteristics that prevent the medical professionals to completely trust the results generated from them. This paper proposes a self-developed CNN model which is comparatively smaller and simpler along with the use of Lime that introduces Explainable AI to the study.
  arXiv  Detail & Related papers  (2021-11-06T13:54:07Z)
• Knowledge Distillation: A Survey [87.51063304509067]
  Deep neural networks have been successful in both industry and academia, especially for computer vision tasks. It is a challenge to deploy these cumbersome deep models on devices with limited resources. Knowledge distillation effectively learns a small student model from a large teacher model.
  arXiv  Detail & Related papers  (2020-06-09T21:47:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.