https://github.com/prsdm/medicalgpt
https://github.com/prsdm/medicalgpt
chatbot chatgpt gpt large large-language-models llms medical phi-2
Last synced: 4 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/prsdm/medicalgpt
- Owner: prsdm
- License: mit
- Created: 2024-09-25T13:34:51.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-18T11:33:52.000Z (over 1 year ago)
- Last Synced: 2024-11-18T12:47:09.021Z (over 1 year ago)
- Topics: chatbot, chatgpt, gpt, large, large-language-models, llms, medical, phi-2
- Language: JavaScript
- Homepage: https://medicalgpt-six.vercel.app
- Size: 1.19 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MedicalGPT 🗣️
This project is built using Next.js and integrates a Medquad (fine-tuned) Large Language Model from Hugging Face🤗.
> [!NOTE]
> This is the sample project on how to deploy LLM models in production, based on this [documentation](https://sdk.vercel.ai/providers/legacy-providers/hugging-face).
The model is trained on a labeled dataset using the Supervised fine tuning (SFT) method. The labeled dataset typically contains examples of instruction (input) and response (output) pairs relevant to the task. In this process, the model learns how to respond to specific instructions.
Check out the Model training part and article here:
[](https://github.com/prsdm/fine-tuning-llms/blob/main/Fine-tuning-phi-2-model.ipynb) [](https://medium.com/@prasadmahamulkar/fine-tuning-phi-2-a-step-by-step-guide-e672e7f1d009)
## Demo
![Demo]()
## Getting Started
#### Clone the repository:
```bash
git clone https://github.com/prsdm/medicalgpt.git
```
```bash
cd medicalgpt
```
#### Install dependencies:
Make sure you have Node.js installed.
```bash
npm install
# or
yarn install
```
#### Then run the development server:
```bash
npm run dev
# or
yarn dev
```
Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
## License
Copyright © 2024, [Prasad Mahamulkar](https://github.com/prsdm).
Released under the [MIT License](LICENSE).