Tutorial Introduction

该教程仅需使用 RTX 4090 即可启动。 

MMed-Llama-3-8B is a multilingual medical large language model developed in 2024 by a research team from Shanghai Jiao Tong University and Shanghai Artificial Intelligence Laboratory. With only 8B parameters, the model has demonstrated performance comparable to large-scale models such as GPT-4, especially in the field of multilingual medicine.Towards building multilingual language model for medicine", and has been published in Nature Communications.

The model is constructed based onLarge-Scale Multilingual Medical Corpus MMedCThe corpus contains about 25.5 billion medical-related tokens in six major languages: English, Chinese, Japanese, French, Russian, and Spanish. The construction of the MMedC corpus aims to provide autoregressive domain adaptation capabilities for general large-scale language models.

MMed-Llama-3-8B model in MMedBench BenchmarkThe performance on the CNN model surpasses existing open source models and is even comparable to GPT-4 in some aspects. In addition, the model also shows strong capabilities in multilingual medical question answering tasks, which shows its effectiveness in dealing with non-English medical problems.

This tutorial is a one-click deployment Demo tutorial for the model. You can directly clone it and open the API address to use it for inference.

---

Effect examples

---

Run steps

1. 在该项目右上角点击「克隆」，随后依次点击「下一步」即可完成：基本信息> 选择算力> 审核等步骤。最后点击「继续执行」即可在个人容器内开启本项目。

2. 等待容器资源分配完成后，可直接使用平台提供的 API 地址进行操作页面的访问（需要提前完成实名认证，此步无需打开工作空间）

3. 与模型进行对话

Discussion and Exchange

🖌️ If you see a high-quality project, please leave a message in the background to recommend it! In addition, we have also established a tutorial exchange group. Welcome friends to scan the QR code and remark [Tutorial Exchange] to join the group to discuss various technical issues and share application effects↓