How does torch.compile() achieve massive speedups despite highly optimized NumPy functions? See how operator fusion makes it fast! ⚡
-
Updated
Jul 3, 2026 - Jupyter Notebook
How does torch.compile() achieve massive speedups despite highly optimized NumPy functions? See how operator fusion makes it fast! ⚡
Training repo for Toy GPT: unigram + small neutral corpus (000_cat_dog.txt)
Training repo for Toy GPT: Context-3 model + small neutral corpus (000_cat_dog.txt)
Training repo for Toy GPT: context-3 model + small structured corpus (001_animals.txt)
Training repo for Toy GPT: unigram model + small structured corpus (001_animals.txt)
Training repo for Toy GPT: bigram model + small domain corpus (010_llm_glossary.txt)
Training repo for Toy GPT: context-2 model + small domain corpus (010_llm_glossary.txt)
Interactive Monte Carlo simulation of the VNAE framework. A visual playground to test how Theta and Beta parameters influence win rates in asymmetric systems.
Training repo for Toy GPT: bigram model + small structured corpus (001_animals.txt)
Training repo for Toy GPT: context-2 model + small structured corpus (001_animals.txt)
Training repo for Toy GPT: Context-3 model with attention + small domain corpus (030_analytics.txt). Attention requires scale.
Training repo for Toy GPT: Context-2 model with embeddings + small domain corpus (030_analytics.txt). Much more efficient use of space.
Training repo for Toy GPT: Context-2 model + small neutral corpus (000_cat_dog.txt)
Training repo for Toy GPT: bigram + small neutral corpus (000_cat_dog.txt)
Training repo for Toy GPT: Context-2 model with attention + small domain corpus (030_analytics.txt). Attention requires scale.
Can a cellular neural network learn how to reliably express meaningful patterns? This is a toy model for a gene regulatory network for cell specification.
🚀 Train a custom unigram model using simple and efficient methods, enabling easy adoption for natural language processing tasks.
Toy models for ordinal realization, residue, selective crystallization, and regime analysis in relational systems.
Claim-bounded reduced-surrogate archive for Socio-Traffic Thermodynamics: stop-and-go waves, synchronization risk, and risk-budgeted information release in toy traffic networks. No policy or deployment claim.
Training repo for Toy GPT: context-3 model + small domain corpus (010_llm_glossary.txt)
Add a description, image, and links to the toy-model topic page so that developers can more easily learn about it.
To associate your repository with the toy-model topic, visit your repo's landing page and select "manage topics."