Tanaka's repositories
go-gbt-tokeniser
A golang port of the gbt tokenizer for extracting tokens and word encodings for the use on a gbt LLM model.
autokeras-demo
A notebook of codebase showing how to train a deep learning model using autokeras which is an automl framework.
binance-data-fetcher
A golang script created for fetching data from the binance exchange.
corpus
Corpus is a wrapper on top of the chroma vector database to allow it to integrate to LLMs so that large text documents can be embedded, indexed and semantically searched.
MERT
Mert is a audio feature extraction model, here is a codebase of how it can be ran and vectors can be created for any audio file.
persistant-vector-db
A persistant vector db that uses chromadb and duckdb to store and query embedded documents
autokeras-experiments
A lis of experimental codebases that uses autokeras which is an automl framework to build advance deep learning system
course-v3
The 3rd edition of course.fast.ai
Dashboard
A dashboard
DevOps-Projects
A dedicated repository on GitHub to showcase my DevOps projects
fine-tuning-jupyter
A collection of jupyter codebases for learning to fine tune machine learning models
go-htmx-template
A template for using htmx and go templates
gorilla
Gorilla: An API store for LLMs
kid-games
a repo of development based kids games for helping young children with developing their technology skills.
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
lit-llama
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
machine-learning-specialization-andrew-ng
A collection of notes and implementations of machine learning algorithms from Andrew Ng's machine learning specialization.
midi-extractor
A script for extracting midi data and converting it into a json format so that it can be used by a machine learning model
next.js
The React Framework
python-flask-api-tutorial
Building an API with Python Flask
stablediffusion-kcv
Codebase showing how to infer and fine tune the keras cv stablediffusion model.
vector-cookbook
Timescale Vector Cookbook. A collection of recipes to build applications with LLMs using pgvector with PostgreSQL and Timescale.