BioGPT™ is a useful AI assistant for biology and medical students and workers. It can better help you write documents in this field. It is powered by microsoft BioGPT model AI(Fine-tuned GPT3-like AI). microsoft BioGPT-Large model. microsoft BioGPT-Large-PubMedQA model. User Guide Enter a medical or biological prompt, and AI will generate a medical or biological description for you according to the prompt. AI output reached 78.2% accuracy on PubMedQA test. For example: [Prompt 1]: COVID-19 is [AI result 1]: COVID-19 is a novel coronavirus that emerged in 2 0 1 9 and has caused over 1 million deaths worldwide. The virus is highly contagious and can be transmitted through direct contact, droplets, and aerosols. The virus is highly pathogenic and can cause severe respiratory illness, including pneumonia, bronchitis, and bronchiolitis. The virus is highly contagious and can be transmitted through direct contact, droplets, and aerosols. The virus is highly pathogenic and can cause severe respiratory illness, including pneumonia, bronchitis, and [Prompt 2]: A 65-year-old female patient with a past medical history of [AI result 2]: A 65-year-old female patient with a past medical history of hypertension, hyperlipidemia, and diabetes mellitus was admitted to our hospital with a chief complaint of sudden onset of left-sided weakness. She had a history of a left middle cerebral artery (MCA) aneurysm clipping surgery 1 0 years ago. On admission, she had left hemiparesis and aphasia. Computed tomography (CT) and magnetic resonance imaging (MRI) showed a left MCA territory infarction. She was treated with intravenous heparin and aspirin. Her About BioGPT Model Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, the lack of generation ability constrains their application scope. In this paper, we propose BioGPT, a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature. We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. Especially, we get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, respectively, and 78.2% accuracy on PubMedQA, creating a new record. Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fluent descriptions for biomedical terms.