Git Product home page Git Product logo

generalization_of_ft-llm's Introduction

Unveiling the Generalization Power of Fine-Tuned Large Language Models

1. Train the model

bash run_train.sh

If you want to fine-tune the model with in-context learning, just change the train.py in run_train.sh to train_ptune.py

2. Evaluate the model on various datasets

bash run_evaluate.sh

3. Assess the performance

Modify the variable prefix in evaluate_cross.py then

python evaluate_cross.py

generalization_of_ft-llm's People

Contributors

lhryang avatar

Stargazers

avatar Pan avatar avatar avatar smellslikeml avatar DongGeon Lee avatar avatar avatar Chufan Shi avatar Jiaqi Xu avatar

Watchers

avatar

Forkers

afisher457

generalization_of_ft-llm's Issues

Question about FTICL

Hello. Thanks for your good work. How do you construct the FTICL data? What's data format of FTICL?
Thanks for your explanation

About training details

Hello.
Thank you for your interesting research.

Can you share the hardware environment for fine-tuning the Llamma2-7b model?
I'm curious about which GPUs and how many were used.
Also, the paper says that the learning rate was set to 0.002, but it is written as 2e-5 in run_train.sh.
What value should I use?

I would appreciate your reply.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.