Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dialoggpt model creation #28

Closed

Conversation

heisenberg16march
Copy link

What are the changes?

Who worked on the changes?

New Components/Features

Enhanced Components/Features

Other Changes/Fixes

Additional Notes

TODOs

heisenberg16march and others added 4 commits May 26, 2024 22:59
Changes Made:
Created chatbot_dialoggpt.ipynb for interacting with the chatbot model.
Developed config.py to manage chatbot configuration settings.
Added environment.yaml for setting up a consistent Conda environment.
Authored README.md with brief project setup, usage, and features.

Contributor:
Varun Muralidharan - Developer and architect of the chatbot components.

New Components/Features:
-Jupyter Notebook for Chatbot: Serves as the primary interface for the chatbot.
-Configuration Management: Facilitates chatbot settings adjustments via config.py.
-Environment Management: Ensures reproducibility of the development environment through environment.yaml.

Enhanced Components/Features:
Not applicable, as all components are newly created.

Other Changes/Fixes:
None, as these are new developments for the project.

Additional Notes:
Future steps include fine-tuning the chatbot model to better suit its intended elderly audience.

TODOs:
Fine-tune the chatbot model to improve response quality.
Expand the dataset with more varied interactions related to elderly care.
Ensure you have Python 3.8 or higher installed, along with pip for managing packages.

### dataset
Data used for training: concatenated_data.csv
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the provenance (original source) of this training file? Do we have permission to use it? Do we have permission to redistribute it?

Data used for training: concatenated_data.csv

## model
This is the most advanced dialoggpt model available in the public library which uses transformers algorithm for its training. Eventough the model is created to chat in a casual manner, this program has customised the model to suit the requirements of the project.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Which public library? What is the origin of this model? What licence is it released under?

Copy link
Member

@ben-AI-cybersec ben-AI-cybersec left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a good start but needs some work for inclusion

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the utility of this file? Why are you using Linear SVC for a chatbot?


## model
This is the most advanced dialoggpt model available in the public library which uses transformers algorithm for its training. Eventough the model is created to chat in a casual manner, this program has customised the model to suit the requirements of the project.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How should the user run this model? You've included a chat.py but also 3 jupyter notebooks? What does each notebook do differently?

@ben-AI-cybersec
Copy link
Member

A lot more documentation and explanation needed, please reopen if you work on this further.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants