# Obtaining the parameters of the zinb/nb distribution

**URL:** <https://discourse.scverse.org/t/obtaining-the-parameters-of-the-zinb-nb-distribution/38>\
**Category:** scvi-tools\
**Created:** [February 16, 2021, 3:08pm UTC](https://discourse.scverse.org/t/obtaining-the-parameters-of-the-zinb-nb-distribution/38 "2021-02-16T15:08:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Frankie](https://avatars.discourse-cdn.com/v4/letter/f/258eb7/32.png) [@Frankie](https://discourse.scverse.org/u/Frankie)\
**Post date:** [February 16, 2021, 3:08pm UTC](https://discourse.scverse.org/t/obtaining-the-parameters-of-the-zinb-nb-distribution/38/1 "2021-02-16T15:08:38Z")

</div>

Hi!

I would like to use your package SCVI for some downstream analysis. I am not sure though, looking over the documentation, if I can obtain the parameters of the nb distribution or zinb distribution after the model has been fitted. Would there be a way to obtain that?

Thank you

---

<div class="post-metadata">

**Author:** ![adamgayoso](https://yyz1.discourse-cdn.com/flex035/user_avatar/discourse.scverse.org/adamgayoso/32/100_2.png) [@adamgayoso](https://discourse.scverse.org/u/adamgayoso)\
**Post date:** [February 17, 2021, 5:25am UTC](https://discourse.scverse.org/t/obtaining-the-parameters-of-the-zinb-nb-distribution/38/2 "2021-02-17T05:25:59Z")

</div>

You should be able to use [this](https://docs.scvi-tools.org/en/stable/api/reference/scvi.model.SCVI.get_likelihood_parameters.html#scvi.model.SCVI.get_likelihood_parameters) function. It returns a dictionary with keys that describe the parameter name.