My LLM Copilot

My Free Personal LLM Copilot

1. Register to start using your free personal LLM copilot.
2. Use your copilot regularly to assist with your tasks in daily work and life.
3. Healthcare professionals can utilize the copilot to support every step of healthcare delivery.
4. Patients can use the copilot to help personalize their healthcare.

My Fine-Tuned LLM Copilot

1. Review the fine-tuned open-source LLMs available on the platform.
2. Choose the fine-tuned LLM that fits your clinical care needs and research goals. Contact us to access your fine-tuned LLM.
3. If your desired fine-tuned LLM is not available, contact us, and we will create a fine-tuned LLM for you.

Choose My Fine-tuned LLM

My Own Open-Source LLM

1. Contact us if you need a private open-source LLM and copilot in your controlled environment. We will validate multiple open-source LLMs for your tasks at no cost.
2. We will deploy your chosen open-source LLM with a chatbot and fine-tune it, if needed, to meet your specific requirements.

How to Create My Own GenAI Copilot?

Start Demo of Personal LLM Copilot

Create and Train My Own LLM Copilot in Three Steps

Start: Register on the platform to begin using your free personal LLM copilot in the cloud and assess its benefits. Select different LLMs in the copilot to compare performance. Healthcare professionals can use the copilot to assist with every step of healthcare delivery, while patients can use it for personalized care.
Deploy: When you need a private open-source LLM in your controlled environment, contact us. Our tech team will validate and compare various versions of top open-source LLMs like Llama 3.1 at no cost. With our technical services, deploy your chosen LLM with a chatbot, such as Gradio, in the cloud or on-premises.
Fine-tune: Use your copilot daily and monitor its performance. We can apply our pioneering ML-enabled learning health system (ML-LHS) unit approach to fine-tune the LLM with your data through continuous learning cycles, improve accuracy and gradually train your LLM chatbot into your trusted, capable GenAI copilot. We have already fine-tuned Llama3.1 for a list of high-impact diseases, allowing you to choose one now to evaluate GenAI's clinical benefits for publishing papers and supporting predictive healthcare.

Note: "My LLM copilot" may refer to one or multiple LLMs and associated chatbots used by you, your team, your department, or your entire my organization to solve problems more effectively.

Why Is It So Easy to Create My Own LLM and Copilot?

The free copilot platform, combined with comprehensive technical support, reduces both the cost and technical barriers, making it accessible for you.

Reduced Cost Barrier:
1. You have two essential questions to answer before deploying your own open-source LLM. The first question is: Can open-source LLMs predict my healthcare tasks accurately or at least at an acceptable level? To answer this, you first need to test the latest versions of the best commercial LLMs to understand the current GenAI limits, including ChatGPT, Gemini, Claude, and Ernie. You may not have access to these paid-version chatbots yourself. However, you can test and compare all of them in the Learning module on this platform for free. Then, you need to easily test several top open-source LLMs to evaluate their performance. The free Multi-LLM Chatbot in the Learning module includes Llama 3.1, Gemma 2, and Mistral open models for you to test.
2. The second question is: Which version of the open model is best for my healthcare tasks? To answer this, you need to compare the performance of different versions of the top open models, which can be time-consuming. Our tech team will conduct the validation study for you free of charge and advise you on selecting the most appropriate open LLM, considering multiple factors, including LLM performance, compute requirements, data safety, and fine-tuning potential.
3. Deploying and running your LLM along with a chatbot will incur some costs. Since our mission is to democratize GenAI for all doctors and reduce healthcare disparities, we strive to minimize these costs for you by all possible means. For example, we provide a Gradio chatbot with open-source LLMs deployed in the cloud for you to test at no charge. Only after your tests confirm the potential of the selected open-source LLM will you decide whether to invest in deploying your own LLM.
Reduced Technical Barrier:
1. For most doctors and healthcare professionals, deploying and running their own LLM is technically challenging without tech support. To address this, our technical team eliminates this obstacle by offering LLM deployment and management as a service.
2. Doctors also require technical support to effectively use their LLM to solve healthcare problems. To remove this technical barrier, our team will help doctors develop the necessary GUI for their healthcare tasks and settings. We will deploy the Gradio chatbot as a starter so that doctors can experiment with their LLMs and gradually define user requirements for their specific applications, likely leading to their own unique GenAI copilot.
3. AI technical expertise is even more critical for LLM fine-tuning. The first challenge is to prepare high-quality training datasets from your patient data using more standardized and consistent data collection approaches. The second challenge is to run effective fine-tuning algorithms with limited compute resources. The third challenge is to evaluate the performance improvement rapidly in a more automated fashion. With our technical support, doctors can reduce their concerns about such technically demanding projects.

Background

Thanks to open-source LLMs like Llama, it has become much more feasible for everyone to have their own LLM. This is especially important for doctors, as they are often required to use LLMs deployed under their full control or that of their organization for patient privacy and data security reasons. Open-source LLM platforms like Hugging Face also make accessing models easier. You can simply select an open-source model, download it for free, and deploy it in your own environment, whether on-premises or in the cloud.

To seamlessly integrate your LLM into your healthcare workflow, you will also need to install a graphical user interface, such as a chatbot, on top of your LLM. Once you test your LLM via a chatbot, you can assess whether the baseline open-source LLM meets your requirements. If it doesn't, you can further improve its performance by fine-tuning it with your patient data, gradually training your LLM and developing your chatbot into your trusted GenAI copilot.

Our mission at the ELHS Institute is to help reduce global health disparities by democratizing GenAI in healthcare. In a review paper invited by JHMHP, we explained why GenAI democratization is intrinsically driven and listed a range of healthcare applications for GenAI. Our initial concept of the GenAI copilot for medical training is outlined in our paper published by JAMA. We have created a more realistic benchmarking system to systematically evaluate top LLMs in diagnostic prediction across most diseases, as presented in our JAMIA paper. Nature published our pioneering study on how to effectively deploy and continuously train machine learning (ML) models in clinical settings using the concept of a ML-enabled learning health system (ML-LHS) unit. By establishing efficient EHR data pipelines for collaborating hospitals, we have helped clinical teams publish ML model papers on several major diseases.

In order to help more doctors, medical students, and healthcare professionals get started with their own LLMs and copilots, we have created the ELHS GenAI Copilot Platform. The platform also enable patients to start using personal LLM copilot for personalized healthcare. Our goal is to help you gradually train your own GenAI copilot to optimize healthcare.

Technical Support

If you need technical assistance, please let us know. We are happy to help you select and deploy your LLM, as well as set up a Gradio chatbot as your starter copilot. We can also assist with fine-tuning your LLM using your data and further training your copilot.