START HEREExplore graph ResidualClassifier4-step tour TensorViz
The residual path #
What happens where the skip path rejoins?
MODEL EXPLORER / CURATED BY TENSORVIZ
29 interactive PyTorch architectures. Follow a guided tour, inspect captured shapes, and take the source back to your own project.
No installation · No Python needed CHOOSE A LEARNING PATH
Start with attention, change one design choice at a time, then connect the pieces in LLaMA.
Follow convolution, residual paths, U-shaped skips and image patches through landmark vision designs.
Explore alignment, bidirectional pretraining, image–text pairing, low-rank adaptation and reasoning post-training.
Compare the GAN game with noise prediction, latent-space denoising and a Transformer diffusion backbone.
Inspect selective recurrent state, Evoformer sequence/pair coupling and promptable mask decoding.
A teaching order, not a claim that each later model adopted every earlier idea.
29 models to explore
Where does an image become a classifier input?
How do queries, keys and values meet?
Component · 2019
What does normalization change in one token vector?
Component · 2020
Why does this feed-forward block split into two branches?
Architecture · 2017
How does a decoder form a next-token distribution?
What happens to the shortcut when normalization moves?
Component · 2023
Which attention heads can share a key/value cache?
Component · 2021
Where does token position enter the attention score?
Inference method · 2022
Can exact attention avoid storing the entire score matrix?
Component · 2024
What must MLA store to avoid reconstructing every key and value?
Component · 2017
How can a token use only part of a larger network?
Training method · 2021
How can two small matrices adapt a frozen linear layer?
Architecture · 2023
Where do RMSNorm, RoPE and SwiGLU meet in an actual decoder block?
Architecture · 2012
How do five convolutions turn an image into a classification vector?
Architecture · 2015
What can flow through a shortcut when a residual branch changes?
How does a segmentation decoder recover features lost during downsampling?
Architecture · 2020
Where does an image become a sequence for a Transformer?
Component · 2014
How does a recurrent decoder decide which source positions to consult?
Architecture · 2018
What changes when the encoder can see both left and right context?
Training method · 2014
Which network is being updated, and what is it trying to change?
Training method · 2020
How does a model learn to reverse corruption?
Architecture · 2021
Why denoise a latent, and where does text enter?
Architecture · 2022
What changes when a Transformer denoises latent patches?
Where do the image and text meet?
How do image features and a user prompt become a mask?
How does the input decide what a recurrent state retains?
How do sequence and pair representations interact before structure is produced?
Training method · 2025
What changes in the learning process while the base architecture stays the same?
Try another idea, or return to the full collection. BRING IT BACK TO YOUR PROJECT
Every model includes its source and a small reproduction recipe. Open your own PyTorch class with tensorViz in VS Code.