Sean Ryan's Projects
Learning algorithms with practice exercises, and links to resources
Bash scripts to read data from Amazon Athena via SQL files. Python scripts to generate charts via Pandas.
SQuAD Question Answering Using BERT, PyTorch - tryout - text summaries
:zap: PowerShell script that lists binary files at the given directory path.
Learn to build an API testing framework in Python
:calendar: Generates images of calendar month tables and can paste them onto suitable photos.
:page_with_curl: Tool to update a CHANGELOG.md file after publishing to npm
Chart-to-Text: Generating Natural Language Explanations for Charts via heuristics
:chocolate_bar: Present histograms (bars!) of images in a directory, including extras such as exif data from the camera. Star and move favorite images.
Common Python utilities for working with files, git, ZIP, lists, processes, dates and times
Notes and links related to the Machine Learning course on Coursera. Assignments are NOT included!
Train a simple text classifier and predict labels - supports ONNX output for performance, language-neutral
Given the name of a property or attribute like 'BrandName' or 'AmountReceived', try to predict a data type like String, Boolean, Integer...
Scripts to auto-deploy SQL from SQL Server and to dump database objects to disk
notes from dev conferences
Classify entities into clusters via embedding vectors, using a given list of category names
:no_entry_sign: A custom eslint rule to ban configurable lists of TypeScript code snippets. examples: "return void reject", "it.only", "debugger".
Example images for the various EXIF orientation flags, in both landscape and portrait orientation.
Fine tune LLaVA 1.5 - based on article by wandb
Showcase of the Gatling Plugin for SBT
:calendar: Bulk process events in a Google Calendar - clean out duplicate URLs and email addresses, move events from one month to the next
:zap: Dynamically generated stats for your github readmes
:green_book: Simple console for Goodreads (get all your book reviews)
Generate comments for source code files, using Chat-GPT
Map natural language instructions to specific commands, suitable for controlling Home Automation or an App
Use LLM to describe a difference graph between versions of a compositional document
Data modelling via natural language using an LLM. Outputs JSON or SQL. Also generates Test data in SQL or CSV format.
Chat with local LLM about your PDF and text documents, privacy ensured [llamaindex and llama3]
Evaluate translations by either a self-hosted Embedder or using Chat-GPT as LLM-as-judge.
Function Calling an LLM taking a bare-bones (no libraries) approach