Giter Site home page Giter Site logo

kishore-fdi / finetuning-autotrain Goto Github PK

View Code? Open in Web Editor NEW
4.0 1.0 2.0 13 KB

This repo fine-tunes the Mistral 7B Sharded model using AutoTrain and QLoRA to create an Customized LLM. It was done with help of PyTorch, Transformers , etc. Contributions welcome! ๐Ÿ˜Š

License: MIT License

Jupyter Notebook 100.00%

finetuning-autotrain's Introduction

Fine-Tuning the Mistral 7B Sharded Model with AutoTrain and QLoRA

Welcome to our project! We're working on fine-tuning the Mistral 7B sharded model with a custom dataset and the orca dataset using AutoTrain and QLoRA. This project aims to create a powerful AI model capable of generating high-quality responses in a conversational setting.

Features

  • Fine-Tuning: We're using the Mistral 7B sharded model as our base, and fine-tuning it to improve its performance on our specific task.
  • AutoTrain: This feature allows us to automate the training process, making it easier to fine-tune our model.
  • QLoRA: QLoRA, or Query Likelihood with Out-of-domain Relevance Augmentation, is a technique we're using to improve the relevance of our model's responses.

Technology Stack

Our project uses a variety of technologies to achieve its goals:

  • Python: The main language used for developing our project.
  • PyTorch: An open-source machine learning library for Python, used for applications such as natural language processing.
  • Hugging Face Transformers: A library that provides general-purpose architectures for Natural Language Understanding (NLU) and Natural Language Generation (NLG).

How to Use

  1. Prepare Your Dataset: Gather the data you'll be using to fine-tune the model. This could be a collection of dialogues, a list of question-answer pairs, or any other type of conversational data.
  2. Fine-Tune the Model: Use the AutoTrain feature to fine-tune the Mistral 7B model on your dataset. This will adjust the model's parameters to better fit your data.
  3. Generate Responses: Once the model has been fine-tuned, you can use it to generate responses. Just input a message, and the model will generate a relevant response!

Contributing

We welcome contributions! If you're interested in contributing, here are a few ways you can help:

  • Data Collection: Help us gather more data to fine-tune our model.
  • Model Training: Assist in the fine-tuning process by training the model on new data.
  • Testing and Feedback: Use our model and provide feedback on its performance.

Contact

If you have any questions or suggestions, feel free to reach out to us. We'd love to hear from you!

Disclaimer

This project is for research purposes only. The generated responses are not meant to provide professional advice or recommendations. Always consult with a qualified professional for any serious matters.

Thank you for your interest in our project! We're excited to see what we can achieve together. ๐Ÿ˜Š

finetuning-autotrain's People

Contributors

kishore-fdi avatar

Stargazers

Ryder Wishart avatar  avatar Karthick.exe avatar Sherma Thangam S 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.