This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene
TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned algorithms within large language models. It provides a standardized framework for wrapping diverse transformer architectures, allowing researchers to extract, manipulate, and analyze internal activations and weights through a consistent interface. The project distinguishes itself through a comprehensive system of activation hooks that can capture, patch, and ablate internal tensors during the forward pass. It includes specialized utilities for decomposing fused projections, material
This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model that trains visual representations using a momentum teacher and self-distillation without the need for labeled data. The library functions as an image feature extractor and visual attention visualizer, allowing for the generation of high-dimensional vectors and the rendering of self-attention maps as heatmaps or videos to analyze model focus. It provides comprehensive tools for downstream vision evaluation, including linear probe classification, k-nearest neighbor categorizatio
This project consists of interactive spreadsheet-based models designed to demonstrate the mathematical mechanics of backpropagation, multi-layer perceptrons, and transformer attention. It serves as an Excel-based neural network simulator for manually calculating tensor operations and matrix multiplications to visualize data flow. The models provide a way to visualize the internal logic of neural networks by implementing self-attention and backpropagation through explicit cell formulas. It includes specific mathematical exercises for modeling transformer architecture and the layers of multi-la
BertViz هي مجموعة أدوات تشخيصية لتصور رؤوس الانتباه وسلوكيات النماذج الداخلية لتفسير كيفية معالجة نماذج اللغات للنصوص. تعمل كأداة قابلية تفسير ومصحح أخطاء لنماذج معالجة اللغات الطبيعية، حيث توفر تحديداً خرائط تفاعلية لآليات الانتباه داخل بنى Transformer.
الميزات الرئيسية لـ jessevig/bertviz هي: Attention Visualizations, Activation Visualizations, Neuron Inspections, LLM Interpretability Dashboards, Latent Attention Analysis, NLP Model Debugging, Transformer Interpretability, Model Execution Debuggers.
تشمل البدائل مفتوحة المصدر لـ jessevig/bertviz: tingsongyu/pytorch_tutorial — This project is a comprehensive collection of educational examples and reference implementations for building vision… transformerlensorg/transformerlens — TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned… facebookresearch/dino — This project is a PyTorch vision transformer framework designed for self-supervised learning. It implements a model… imagineailab/ai-by-hand-excel — This project consists of interactive spreadsheet-based models designed to demonstrate the mathematical mechanics of… openai/transformer-debugger — This project is a language model interpretability tool designed to visualize and analyze the internal activations and… tensorspace-team/tensorspace — Tensorspace is a WebGL-based 3D visualization framework and renderer designed to map deep learning model architectures…