Coder Social home page Coder Social logo

semaj87 / summarise-dialogue-flan-t5 Goto Github PK

View Code? Open in Web Editor NEW
1.0 1.0 0.0 285 KB

Performing the task of dialogue summarisation using Generative AI, whilst comparing the effects of zero shot, one shot and few shot prompt engineering. These steps are used to enhance the completion of Large Language Models (LLMs))

License: MIT License

Shell 2.15% Jupyter Notebook 97.85%
flan-t5 generative-ai huggingface-datasets huggingface-transformer machine-learning prompt-engineering dialogue-sum huggingface

summarise-dialogue-flan-t5's Introduction

Summarising dialogue using FLAN-T5

This is a simple project that was undertaken to perform the task of dialogue summary using Generative AI. Through the use of different techniques to inference process, the exploration of how different prompts can affect the completion of the model were performed. Prompt engineering was carried out, by comparing zero shot, one shot and few shot inferences, with the intention to see how to best enhance the generative output of the LLM. This is part of Adapt & Align model, which is only one of ghe steps involved during the generative AI project lifecycle. Additional changes were also made to the configuration parameters, to best understand the influence they make, in terms of the model's ability to make a final decision about next word generation. Configuration parameters that were changed: do_sample, temperature, top_k & top_p

Generative AI project lifecycle

Generative AI project lifecycle

Model and dataset

Model: FLAN-T5
Dataset: DialogueSum

Prerequisites

  • Python3
  • Jupyter
  • Hugging Face
  • PyTorch

License

Distributed under the MIT License. See LICENSE for more information.

summarise-dialogue-flan-t5's People

Contributors

semaj87 avatar

Stargazers

 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.