Scaled Dot-Product Attention (SDPA) might immediately pop into the minds of those familiar with the Transformer self-attention mechanism:
I often use my computer to watch full-screen videos and need to promptly return to work mode when the time comes — but embarrassingly, I don’t like constantly picking up my phone to check the current time, as it’s quite inconvenient.
Read More »[Linux] tty-clock: A Tool For Displaying Electronic Clock Time On Terminal
Cross-lingual Modular (X-Mod) is an interesting language model architecture that modularizes the parameters for different languages as Module Units, allowing the model to use separate parameters when fine-tuning for a new language, thereby (comparatively) avoiding the problem of catastrophic forgetting.
Read More »[Paper Reading] Lifting the Curse of Multilinguality by Pre-training Modular Transformers
When using ComfyUI to generate images, we need to leverage the capabilities of various models to ultimately form a complete workflow. In other words, these so-called various models together constitute what we call Stable Diffusion. Today, I will introduce where to download these models.
Read More »Stable Diffusion ComfyUI Note 03 – How To Download SD Models
Singular Value Decomposition (SVD) is a method for decomposing a matrix into three matrices, revealing the rank, data dimensions, and key directions of the original matrix. It is often used in dimensionality reduction, compression, and structural analysis.
Read More »Note Of Singular Value Decomposition (SVD)
The year 2023 witnessed an explosion of generative AI technologies, with a myriad of applications emerging across various domains. In the field of Natural Language Processing (NLP), Large Language Models (LLMs) stand out as one of the most significant advancements. By training LLMs effectively and reducing hallucinations, they can significantly reduce human effort across a wide range of tasks.
Read More »[Paper Reading] RAGAS: Automated Evaluation of Retrieval Augmented Generation
Recently, due to work requirements and the fact that some Steam games run more smoothly on Windows, I seriously considered reallocating 200GB of disk space for Windows on my Linux laptop. However, since I initially allocated the entire 1TB SSD to Linux, I now have to resize the partitions.
Read More »[Linux] Using `gparted` Or `parted` To Resize Disk Partition
When we purchase a new hard drive or evaluate whether to use one, the read/write speed of the hardware is definitely our main concern, as it directly affects our usage experience with the drive.
Read More »[Linux] Using Command Line Tools To Test Hard Disk Read/Write Speeds
CuPy is an open-source GPU-accelerated numerical computation library designed for deep learning and scientific computing. It shares many of the same methods and functions as the popular NumPy package in Python but extends its capabilities to perform computations on the GPU. In short, tasks that can benefit from parallel computation on the GPU, such as matrix operations, can achieve significant acceleration with CuPy.
Read More »Using CuPy to Accelerate Matrix Operations with GPU
If we happen to have several remote servers with different IPs and wish to browse the web through these different IPs (for example, some services may not support local or national access), we can use SOCKS proxy ports and configure Firefox to browse the web using the IPs of these remote servers without needing to install other VPN tools.
Read More »[Linux] Using SSH to Set Up SOCKS Proxy Port for Firefox to Browse the Web via Remote Server IP
