Andreas Kirsch (@BlackHC)

Top repositories

1

tfpyth

Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).
Python
641
star
2

llm-strategy

Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types
Python
376
star
3

toma

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory
Python
354
star
4

BatchBALD

Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.
Python
219
star
5

dart_repl

Proof of concept REPL shell for Dart
Dart
81
star
6

batchbald_redux

Reusable BatchBALD implementation
Jupyter Notebook
71
star
7

mdp

Make it easy to specify simple MDPs that are compatible with the OpenAI Gym.
Python
37
star
8

mnist_by_zip

Compression algorithms (like the well-known zip file compression) can be used for machine learning purposes, specifically for classifying hand-written digits (MNIST)
Jupyter Notebook
35
star
9

llmtracer

Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp
Python
12
star
10

player_of_jeopardy

ChatGPT can solve Jeopardy! clues really well!
Python
10
star
11

chatplayground

Chat Playground for LLMs
Python
9
star
12

ddu_dirty_mnist

Dirty-MNIST dataset introduced in "Deterministic Neural Networks with Inductive Biases Capture Epistemic and Aleatoric Uncertainty" (https://arxiv.org/abs/2102.11582)
Jupyter Notebook
7
star
13

pbt

Jupyter notebooks to play around with population based training, as described in https://arxiv.org/abs/1711.09846
Jupyter Notebook
7
star
14

blackboard-pagi

Python
7
star
15

2302.08981

Jupyter Notebook
5
star
16

batch_pong_poc

Instead of running one environment at a time or one per thread, run everything in batch using numpy on a single core.
Jupyter Notebook
4
star
17

hello-slurm

Shell
4
star
18

pytorch_datadiet

Python
3
star
19

laaos

Logs as append-only source.
Python
3
star
20

implicit_lambda

This package adds support for implicit lambdas, so you can write `map(_ + 5, a_list)` instead of `map(lambda x: x + 5, a_list)`.
Python
3
star
21

dlb_chapter2

TeX
1
star
22

WML

Whitespace Markup Language
C++
1
star
23

2020_ebm_presentation

A presentation about EBMs and Hopfield networks @ OATML
HTML
1
star
24

2202.01851

Repository for 'A Note on "Assessing Generalization of SGD via Disagreement"'
Jupyter Notebook
1
star
25

algo_fairness

Jupyter Notebook
1
star
26

2208.00549

Unifying Approaches in Data Subset Selection - Experiments
Jupyter Notebook
1
star