https://github.com/americast/epigpt

https://github.com/americast/epigpt

Last synced: 30 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/americast/epigpt
• Owner: americast
• License: mit
• Created: 2023-11-28T22:56:21.000Z (12 months ago)
• Default Branch: epi
• Last Pushed: 2023-12-06T03:34:25.000Z (11 months ago)
• Last Synced: 2024-06-02T10:23:40.259Z (5 months ago)
• Language: Jupyter Notebook
• Size: 92.4 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# EpiGPT

Note: Please issue `cd src` as all the commands below should be run from the `src` directory.

## Forecaster

### Installlation

Run the following command to install all dependencies in a conda environment named `llmtime`. Change the cuda version for torch if you don't have cuda 11.8. 

```

source install.sh

```

After installation, activate the environment with

```

conda activate llmtime

```

If you prefer not using conda, you can also install the dependencies listed in `install.sh` manually. 

Finally, add your openai api key to `~/.bashrc` with

```

echo "export OPENAI_API_KEY=" >> ~/.bashrc

```

Now run

`pip install -r requirements.txt`

### Running the code

```bash

./run_epi.sh

```

### Results and plots

```

python evaluate_epi.py

```

Plots are saved in `epi_plots` directory.

### Example plot

![image](src/outputs/monash/cdc_flu.png)

## Summarizer

Try the three different difficulty levels of prompts in Epi2Text, and you can make any LLM summarize the 2023 ILINet data.