Skip to content

arnavk23/AWS-Sagemaker-IT-Domain

Repository files navigation

AWS-Sagemaker-IT-Domain

Imagine you are an AI engineer. Your team is exploring innovative ways to enhance customer experience and streamline information delivery. You've been entrusted by your boss to develop a proof of concept (POC) for a domain expert model. This model will be trained on a dataset of domain-specific knowledge (finance, medical, or IT domain knowledge). The model can then be used to create chat applications, internal knowledge applications, or text content generation for company collateral.

Project Objective

Your task in this project is to train (fine-tune) a large language model. This model should become a domain expert, capable of generating informative, accurate, and contextually relevant text responses. Think of it as creating a knowledgeable consultant for the company!

The Challenge

Selecting the Dataset: Choose an appropriate, copyright-free unstructured text dataset relevant to a domain. You'll choose from finance, medical, or IT datasets. This dataset will be the training ground for your model to learn domain-specific language and concepts.

Overview of Project Tasks

Fine-tuning the Language Model: Utilize Amazon Sagemaker and other AWS tools to fine-tune the Meta Llama 2 7B foundation model. This model has been trained for text-generation tasks. The goal is to adapt this model to your selected domain, enhancing its ability to understand and generate domain-specific text. Deliverables

Trained Model: A fine-tuned language model proficient in your chosen domain. Report and Presentation: Documentation of your process, challenges, and solution.

About

Done during Gen AI course of AWS on Udacity

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published