Generates ChatGPT/BingChat & GPT-3 prompts using this model trained by Kaludi.
Enter a role and a prompt will be generated based on it.
Click Here To View This App Online!
- Generate prompts based on a role entered by the user
- Uses a pre-trained language model to generate the prompt
To use the app, simply enter a role in the input field and click on the "Generate" button. A prompt will be generated based on the role entered.
Some examples of roles that can be entered:
- Virtual Assistant
- Customer Service Representative
- Personal Assistant
- Data Scientist
The app uses Streamlit for the user interface and the Hugging Face Transformers and is a fine-tuned version of philschmid/bart-large-cnn-samsum's model using this dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.2214
- Validation Loss: 2.7584
- Epoch: 4
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.1982 | 2.6801 | 0 |
| 2.3601 | 2.5493 | 1 |
| 1.9225 | 2.5377 | 2 |
| 1.5465 | 2.6794 | 3 |
| 1.2214 | 2.7584 | 4 |
- Python 3.6 or higher
- Streamlit
- Transformers (Hugging Face)
- Clone the repository:
git clone https://github.com/Kaludii/ChatGPT-BingChat-GPT3-Prompt-Generator.git
- Install the required packages:
pip install streamlit transformers
- Run the app:
streamlit run app.py