https://github.com/fatemafaria142/Instructions-Tuning-Across-Various-LLMs-with-Alpaca-Dataset

https://github.com/fatemafaria142/Instructions-Tuning-Across-Various-LLMs-with-Alpaca-Dataset

Last synced: 3 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/fatemafaria142/Instructions-Tuning-Across-Various-LLMs-with-Alpaca-Dataset
• Owner: fatemafaria142
• Created: 2024-01-10T08:44:36.000Z (12 months ago)
• Default Branch: main
• Last Pushed: 2024-01-18T18:55:51.000Z (12 months ago)
• Last Synced: 2024-01-18T20:13:33.770Z (12 months ago)
• Language: Jupyter Notebook
• Size: 166 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome_ai_agents - Instructions-Tuning-Across-Various-Llms-With-Alpaca-Dataset - I utilized the "Alpaca" dataset, which comprises 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003 engine (Building / Datasets)
• awesome_ai_agents - Instructions-Tuning-Across-Various-Llms-With-Alpaca-Dataset - I utilized the "Alpaca" dataset, which comprises 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003 engine (Building / Datasets)

README

        
Improved-Language-Model-Instructions-Tuning-using-Alpaca-Dataset


In this project, I explored different prompt types for Large Language Models.


Alpaca Dataset

I utilized the "Alpaca" dataset, which comprises 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003 engine. This instruction data is ideal for conducting instruction-tuning for language models, enhancing their ability to follow instructions effectively.

Dataset Link: Alpaca Dataset


Large Language Models (LLMs)

I employed six different types of Large Language Models for this task. Here are the details along with their respective links:




  


    
GPT2

    
Model Link: GPT2 Documentation

  

  


    
GPT-Medium

    
Model Link: GPT-Medium

  

  


    
Mistral-7B-v0.1

    
Model Link: Mistral-7B-v0.1

  

  


    
TinyLlama-1.1B-Chat-v1.0

    
Model Link: TinyLlama-1.1B-Chat-v1.0

  

   


    
Mistral-7B-Instruct-v0.2

    
Model Link: Mistral-7B-Instruct-v0.2

  

   


    
Starling-LM-7B-alpha

    
Model Link: Starling-LM-7B-alpha

  



Feel free to explore these models and the Alpaca dataset for a deeper understanding of the project's advancements in language model instruction tuning.