-
CHOP Radiology Machine Learning Engineer
- Philadelphia, PA
- https://www.linkedin.com/in/mjwelsh99/
Block or Report
Block or report MichaelJWelsh
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
A Python framework for high performance GPU simulation and graphics
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
Video+code lecture on building nanoGPT from scratch
YOLOv10: Real-Time End-to-End Object Detection
Structured state space sequence models
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)
A TensorFlow.js based AI player platform for T-Rex Runner. T-Rex Runner is originally an easter egg game inside chrome.
RAG (Retrievel Augmented Generation) implementation using ChromaDB, Mistral-7B-Instruct-v0.1 and gte-base for embeddings.
the AI-native open-source embedding database
Create and modify nginx serverblock configs in Python
Fast and memory-efficient exact attention
A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Accessible large language models via k-bit quantization for PyTorch.
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions
A library for efficient similarity search and clustering of dense vectors.
A Deep Learning Python Toolkit for Healthcare Applications.
Ensembling neural networks for improved prediction and privacy in early diagnosis of sepsis
PubMed scraper for async search on a list of keywords and concurrent extraction of all found URLs, returning a DataFrame/CSV containing all article data (title, abstract, authors, affiliations, etc)
Bootstrap example of a Flask app served via Gunicorn and Nginx using Docker conteiners
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.