[Paper Reading] ENTP: ENCODER-ONLY NEXT TOKEN PREDICTION
The following are some points in this paper:
Read More »[Paper Reading] ENTP: ENCODER-ONLY NEXT TOKEN PREDICTIONClay
[Solved] Uvicorn Closed In Container - HTTP connection lost. Shutting down, exit 0
Problem Description
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
[Machine Learning] Note Of Kullback-Leibler Divergence
What is KL Divergence?
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
[Linux] `ncdu` Disk Usage Analyzer Tool Note
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.
[Python] Using Locust Open Source Load Testing Framework for Stress Testing
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
Notes on Fine-Tuning a Multi-Modal Large Language Model Using SFTTrainer (Taking LLaVa-1.5 as an Example)
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)
"Common sense, as people call it, is merely the biases learned during youth"—the training data for AI models is no different
This year, due to work, I tried annotating the data myself; it was only after diving into it personally that I truly understood just how profoundly training data affects an AI model.
Read More »"Common sense, as people call it, is merely the biases learned during youth"—the training data for AI models is no different
[Python] Extracting Text from PPT Using the python-pptx Library
Introduction
Recently, while handling some work-related matters, I noticed that the client might potentially need a way to extract text from PPT files. I discussed this with the PM and my supervisor, and they mentioned that the client could simply copy the text from the PPT slides manually. Unless the client explicitly requests us to extract it programmatically.
Read More »[Python] Extracting Text from PPT Using the python-pptx Library
[Machine Learning] Vector Quantization (VQ) Notes
The first time I heard about Vector Quantization (VQ) was from a friend who was working on audio processing, which gave me a vague understanding that VQ is a technique used for data feature compression and representation. At that time, I still wasn't clear on how it differed from dimensionality reduction techniques like PCA.
Read More »[Machine Learning] Vector Quantization (VQ) Notes
[Linux] Use the batcat Command as a Replacement for cat, Highlighting Code or Configurations
batcat or simply bat, is a replacement tool for the cat command. It retains the functionality of cat for displaying files, while also highlighting keywords in code or configuration files, making it more convenient for developers to browse daily tasks or code files (thus, it's definitely a productivity tool!).