Stefan Rummer's starred repositories
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
hands-on-llms
🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴
Company-Analysis-Model
Documentation behind the model used to analyse companies in Simply Wall St
streamlit-aggrid
Implementation of Ag-Grid component for Streamlit
differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library
example-scripts
A collection of scripts and notebooks to help you get started quickly.
codex_py2cpp
Converts python code into c++ by using OpenAI CODEX.
magma
MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multilingual models from Aleph Alpha check out our website https://app.aleph-alpha.com
realtime-bakllava
llama.cpp with BakLLaVA model describes what does it see
the-BPM-detector-python
BPM detection for audio files (currently just .wav). Takes in the whole file, and prints out the BPM.
homework_fall2021
Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2021)
chat-with-page
Chrome extension to chat with page using local LLM (llama, mistral 7B, etc)
streamlit-heroku
Dockerizing streamlit application and deploying it on heroku.
LibreTranslate-py
Python bindings to connect to a LibreTranslate API
python3-linkedin
Python3 interface to the LinkedIn API
streamlit-nested-layout
Allows columns and expanders to be nested
streamlit-pills
💊 A Streamlit component to show clickable pills/badges
streamlit-embedcode
Streamlit component for embedding code snippets such as GitHub gists, CodePen snippets, Gitlab snippets, etc.
AI-Makerspace
AI Makerspace: Blueprints for developing machine learning applications with state-of-the-art technologies.
awesome-machine-learning-startups-munich
A list of machine learning & artificial intelligence startups in Munich (Germany)
emotion-recognition
This is the repository for my master's thesis on emotion detection
differential-ml
Tensorflow and Pytorch implementation of differential machine learning (https://arxiv.org/abs/2005.02347, by Brian Huge and Antoine Savine).
DPBenchmark
A modular codebase for the benchmarking of popular machine learning design choices in differentially private learning systems. Codebase for the Paper: SmoothNets: Optimizing CNN architecture design for differentially private deep learning