Pinned Repositories
text2dataset
Easily turn large English text datasets into Japanese text datasets using open LLMs.
cos
cos is a toy operating system in C Language with reference to https://operating-system-in-1000-lines.vercel.app
fast-near-duplicate-matching
Fast near-duplicate matching is a method for quickly finding near-duplicate spans in a document by utilizing the Rabin-Karp algorithm.
goindexSearch
goindexsearch is a package that can do go vet and grep for all packages in https://index.golang.org/index
gomicollector
gomicollector is a simple mark-sweep garbage collector in Rust.
input-method
First-two-char input method using transformer-based language model and n-gram model.
jax-llm
JAX implementation of Large Language Models. You can train GPT-2-like model with 青空文庫 (aozora bunko-clean dataset) or any other text dataset.
jaxkan
JAX implementation of Kolmogorov Arnold Networks (KANs).
llava-mnist
llava-mnist is a simple example of Vision and Language model using LLaVA architecture trained on MNIST dataset.
multierr-analysis
multierr static analysis
speed1313's Repositories
speed1313/cos
cos is a toy operating system in C Language with reference to https://operating-system-in-1000-lines.vercel.app
speed1313/gomicollector
gomicollector is a simple mark-sweep garbage collector in Rust.
speed1313/jax-llm
JAX implementation of Large Language Models. You can train GPT-2-like model with 青空文庫 (aozora bunko-clean dataset) or any other text dataset.
speed1313/jaxkan
JAX implementation of Kolmogorov Arnold Networks (KANs).
speed1313/bioflax
bioflax provides a JAX implementation of biologically plausible learning algorithms
speed1313/input-method
First-two-char input method using transformer-based language model and n-gram model.
speed1313/mcmc
Learning about Markov chain Monte Carlo.
speed1313/mislabel-unlearning
The code for the domestic conference paper, "Improving Generalization Performance of Trained Models by Unlearning Mislabeled Data"
speed1313/ntk
experiments about the neural tangent kernel
speed1313/fast-near-duplicate-matching
Fast near-duplicate matching is a method for quickly finding near-duplicate spans in a document by utilizing the Rabin-Karp algorithm.
speed1313/llava-mnist
llava-mnist is a simple example of Vision and Language model using LLaVA architecture trained on MNIST dataset.
speed1313/paperguessr
Guess the title of the paper from the reference section.
speed1313/AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
speed1313/blog-comment
speed blog's comment space
speed1313/blog-dashboard
speed1313/deep-learning-from-scratch-5
speed1313/gnnbook
書籍『グラフニューラルネットワーク』のサポートサイトです。
speed1313/hub-docs
Docs of the Hugging Face Hub
speed1313/innshi
This is my example solution to programming implementation questions in the Entrance Examination for the Master's Program in the Department of Communications and Computer Engineering at the Graduate School of Informatics, Kyoto University.
speed1313/llm-jp-tokenizer
speed1313/LLMs-from-scratch
Implementing a ChatGPT-like LLM from scratch, step by step
speed1313/operating-system-in-1000-lines
Writing an OS in 1,000 lines.
speed1313/optimal-transport
optimal transport
speed1313/paperguessr-backend
speed1313/pythia
The hub for EleutherAI's work on interpretability and learning dynamics
speed1313/RAGs
RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems
speed1313/reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
speed1313/synthesized-datasets
speed1313/Tensor-Puzzles
Solve puzzles. Improve your pytorch.
speed1313/uvadlc_notebooks
Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023