Metadata-Version: 2.1
Name: modelflows
Version: 0.0.1
Summary: Conditional normalizing flows for emulating grids of stellar models
Home-page: https://github.com/mtyhon/modelflows
Author: Marc Hon
License: MIT
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: pandas
Requires-Dist: tqdm
Requires-Dist: corner
Requires-Dist: matplotlib
Requires-Dist: torch >=2.0.0
Requires-Dist: scikit-learn >=1.3.0
Requires-Dist: arviz >=0.12.1
Requires-Dist: zuko ==0.3.2

# modelflows
Normalizing Flows for the Emulation of Grids of Stellar Models

To run the experiments in the notebooks, please download the grid of models [here](https://www.dropbox.com/scl/fi/yyfl98nrygg692t807uae/grid.zip?rlkey=6ausvk1wtk7r2vgc95cpdgv3m&dl=0) and the trained conditional normalizing flows (CNF<sub>dwarf</sub>, CNF<sub>giant</sub>, and CNF<sub>asfgrid</sub>) 
[here](https://www.dropbox.com/scl/fi/fvfzzcxojwv56bfable90/pretrained_flows.zip?rlkey=0pka2ddu9s0j61dk5xxsotmws&dl=0). Unzip these files into the main folder. The grid is optional, but necessary to visualize comparisons with its emulation.

An interactive app can be found [here](https://mtyhon--modelflows-inyou.modal.run/).

![varymassfeh](https://github.com/mtyhon/modelflows/blob/main/images/varymassfeh.gif)


A pip-installable package `modelflows` is available!


## 

