ColBERT is an embedding model designed specifically for retrieval tasks, transforming the tokens of Queries and Documents into embeddings and computing the maximum similarity.
Read More »[Paper Reading] ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
Hadolint is a Dockerfile linter that helps you follow best practices and style guidelines when writing Dockerfiles.
Read More »[Linux] How To Use Hadolint To Avoid Terrible Dockerfile
To this day, many AI applications and open-source projects are developed based on the HuggingFace transformers package. A large number of models and packages are written to be compatible with the transformers format, and even share the same functions and methods, which makes them more widely accepted.
Under this premise, I came across an open-source training framework that conveniently wraps the automatic reading of Transformer architectures. However, one unavoidable problem is I want to use my custom model for experiments. I tried several solutions, hoping that when using AutoModel.from_pretrained(), by simply providing the local path to my model, I could successfully use my custom model architecture. This article records the method that worked.
When building deep learning models in PyTorch, adjusting the shapes of layers and input/output dimensions is something every AI engineer has to deal with. However, there is a small but interesting pitfall in the view() method of PyTorch:
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.Read More »[Solved] RuntimeError: view size is not compatible with input tensor’s size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(…) instead.
Recently, I started experimenting with Flutter to develop desktop applications. Since I’m using the Linux Gnome desktop, its default system window bar (the top strip) is completely black, which doesn’t match the light and playful tone of the app I’m developing. So, I found a great tool: bitsdojo_window.
Read More »[Flutter] Using bitsdojo_window to Customize Window Title Bar
The working principle of LayerNorm is as follows:
Read More »[Machine Learning] Note of LayerNorm Cross entropy is a very common loss function in Machine Learning, as it is able to quantify the difference between a model’s classification predictions and the actual class labels, particularly in ‘classification tasks’.
Read More »[Machine Learning] Note of Cross Entropy Loss Gaussian Error Linear Unit (GELU) is an activation function used in machine learning. While it resembles the classic ReLU (Rectified Linear Unit), there are some key differences.
Read More »[Machine Learning] Note of Activation Function GELU RMSNorm is an improvement over LayerNorm, often used in the Transformer self-attention mechanism. It aims to mitigate the issues of vanishing and exploding gradients, helping the model converge faster and improve performance.
Read More »[Machine Learning] Note of RMSNorm
(Note: Since this article is imported from my personal Hackmd, some symbols and formatting might not display properly in WordPress. I appreciate your understanding, sorry for any inconvenience.)
RoPE is a method for introducing relative position information into the self-attention mechanism through absolute positional encoding.
Read More »[Machine Learning] Note of Rotary Position Embedding (RoPE)
