Finetune Llama3.2 Vision Model On Databricks Cluster With VPNRecently I’ve been working on an initiative to finetune llama3.2 vision model on a custom dataset so that the model can result in a better…Oct 15Oct 15
Parse a multi-line string as a json in JenkinsAs one of the most popular open source CI/CD tools, Jenkins is widely used in industry to automate the deployment and update of service…Oct 9Oct 9
Why is ‘high dimension’ a curse to machine learning?In the world of machine learning, data is an indispensable part to instill knowledge into machine learning models, making it able to…Jan 15, 2023Jan 15, 2023
10 Linux Commands that every data scientist should knowRanked 3rd in Best Tech Jobs, data science has been a hot topic in the past few years. As more and more companies have broader requirements…Jan 8, 20231Jan 8, 20231
18 Git Commands that every software engineer should knowGit is often the go-to platform to keep track of any changes from other developers and monitor the version of any model product with…Dec 23, 2021Dec 23, 2021
How to merge a group of CSV files with different columns into a DataFrameIn this story, I will go over the steps to merge a group of CSV into a DataFrame and export it into a CSV file.Aug 27, 2020Aug 27, 2020
A complete solution manual for Started hold until boot finishes up issue.If you were a frequent Ubuntu user, you may sometimes encounter the “started hold until boot finished up” issue when you tried to reboot…Aug 6, 20201Aug 6, 20201
Text Tokenization, Lemmatization in Natural Language Processing (NLP)This dialogue comes from ELIZA, a early language processing system that only carry a limited number of conversations. As the creator…May 4, 2020May 4, 2020
