To consolidate this week's knowledge, students should complete the following project:
- Create a GitHub repository for your project
- Add all group members as collaborators
- Create a README.md file with your project description
- Use the
story-telling-app
as a base repository or create a new application from scratch using NextJS - Implement a table of characters that users can create for the story
- Users should be able to add, edit, and delete characters
- Each new character should have a name, description, and personality
- Customize the prompt to generate a story using user-created characters, if any
- Implement a summary of each character's role in the story after the full text has been generated
- Test different models for story generation and compare their outputs
- Evaluate how well the models "remember" user-created characters
- Experiment with different context window sizes across models to observe their impact on output
- Test models of varying sizes and observe how this influences the output
- Use models compatible with your device, focusing on the experiment rather than overall story quality
- Submit your project via the submission form
- add OpenAI API Key to
.env.local
- or use local AI backend
- git clone this repo
- cd into the directory
- install dependencies
git clone [email protected]:alefinvest/q4-w2-homework.git
cd q4-w2-homework
npm install
First, run the development server:
npm run dev
Open http://localhost:3000 with your browser to see the result.
Run the Text Generation UI. The API will be available in http://127.0.0.1:5000/
Story generated with llama-2-7b-chat.Q4_K_M.gguf:
Story generated with Phi-3.5-mini-instruct:
This homework has been done by the following members of GROUP 15: