Today, while I was eating, I came across a video (the video is attached at the end of this article). Unlike many tech channels that jump straight into discussing AI, economics, and replacing humans, this video took a more careful approach. It explained in detail how hardware specifications have influenced algorithms (or AI model architectures) over time.
Read More »Here’s a thought: Will Transformers be replaced in the future?
We usually start various services on Linux servers, the most common being hosting a website or opening a port to allow us or users to test developing functionalities.
Read More »[Linux] How To Check The Port is Used?
I've been intermittently reading about a fine-tuning method called Kahneman-Tversky Optimization (KTO) from various sources like HuggingFace's official documents and other online materials. It's similar to DPO as a way to align models with human values, but KTO's data preparation format is much more convenient, so I'm quickly applying it to my current tasks before making time to study the detailed content in the related papers.
Read More »Note Of KTOTrainer (Kahneman-Tversky Optimization Trainer)
Podman is an open-source tool designed to manage containers and images. Its full name is Pod Manager tool (podman). While Podman is similar to Docker, there are a few key differences in its design.
Read More »[Linux] [Linux] Podman Basic Command Note
The following are some points in this paper:
Read More »[Paper Reading] ENTP: ENCODER-ONLY NEXT TOKEN PREDICTION
Today, while I was using podman to create a container (from a FastAPI image) to run my FastAPI service, I encountered an issue where the container would automatically stop if the user logged out or if there were no HTTP POST requests sent to the API for a while. After some time, the service would stop.
Read More »[Solved] Uvicorn Closed In Container - HTTP connection lost. Shutting down, exit 0
In machine learning, we often encounter the term KL Divergence (also known as Kullback-Leibler Divergence). KL Divergence is a metric used to evaluate the difference between two probability distributions P and Q.
Read More »[Machine Learning] Note Of Kullback-Leibler Divergence ncdu is a disk usage analyzer tool based on NCurses, mainly used to view and manage disk space. It provides a terminal interface to browse the directory structure, allowing users to quickly explore directories and see the size of each file or folder. This helps users identify directories or files that are taking up a large amount of space.
Locust is an open-source load testing tool that helps simulate heavy user traffic on web applications and APIs. Compared to traditional load testing tools, Locust offers more customization and scalability—it supports Python as the scripting language, allowing us to write tests specific to our API or web service use cases.
Read More »[Python] Using Locust Open Source Load Testing Framework for Stress Testing
A multi-modal large language model (Multi-Modal Large Language Model) isn’t limited to text only. I know this might sound contradictory, but this is a term that has become widely accepted. What I want to document today is how to fine-tune a multi-modal model using a script.
Read More »Notes on Fine-Tuning a Multi-Modal Large Language Model Using SFTTrainer (Taking LLaVa-1.5 as an Example)
