David Marx's repositories
Multi-Modal-Comparators
Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP
zero-shot-intent-classifier
Minimal zero-shot intent classifier for arbitrary intent slot filling, via LLM prompting w LangChain.
not-a-package-manager
utilities to facilitate working with codebases that don't ascribe to normal package management paradigms, e.g. ML research code that can be cloned but not installed.
ai-ethics-in-the-wild
some stuff that's worth talking about
keyframed_chatgpt
An experiment pair-programming with ChatGPT. Reference the commit-to-commit diffs to see how this developed each step of the way.
advent-of-code-2022
https://adventofcode.com/2022
clip-auto-organizer
fuck it, why not - https://github.com/dmarx/bench-warmers/blob/main/clip_auto_organizer.md
1click-hpc
Deploy your HPC Cluster on AWS in 20min. with just 1-Click.
clip-retrieval
Easily compute clip embeddings and build a clip retrieval system with them
consistency-models
A JAX implementation of the continuous time formulation of Consistency Models
einops-exts
Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️
hard-prompts-made-easy
to do: experiment with replacing random prompt init image captioner e.g. BLIP
micro-agent
A tiny implementation of an autonomous agent powered by LLMs (OpenAI GPT-4)
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
rust_too_many_lists
following the tutorial here: https://rust-unofficial.github.io/too-many-lists/
sample-generator
Tools to train a generative model on arbitrary audio samples
stability-sdk
SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)
Tensor-Puzzles
Solve puzzles. Improve your pytorch.