miniforge VS mamba

Nope they don't use venv for any of the oobabooga# variants nor is it recommended for the git version. I'm using https://github.com/conda-forge/miniforge#mambaforge-pypy3 (better version of the recommended conda) for the git variant. The oobabooga* variant uses micro/miniconda (I suck with names) which you can easily drop into with cmd_?something? and does it all internally. Like whoever built that whole environment setup for the _windows/linux/mac did a great job.

wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-aarch64.sh .

Mambaforge!

Just to further clarify: you don't need mamba to avoid the Anaconda distribution. The place you get mambaforge also supplies (and originally supplied) miniforge, which is miniconda with conda-forge set as the default channel. All the *forge installers do in this regard is automatically set conda-forge as the default (and only) channel, which is something one can do manually with miniconda.

I'd recommend using miniforge if you're comfortable with CLIs, otherwise https://www.anaconda.com/.

Tip 1: To use less of your Codespaces resources start with a smaller image like Miniconda or Miniforge and install only what you need.

miniforge, no need to deal with conda environments anymore. https://github.com/conda-forge/miniforge

>"everyone" seems to know Mamba. I never heard of Mamba

Only the "everybody who knows what mamba is" are the ones upvoting and commenting. Think of all the people who ignore it. For me, Mamba is the faster version of Conda [1], and that's why I clicked on the article.

https://github.com/mamba-org/mamba

Yes, this is a big disadvantage. But have you tried Mamba that aims at implementing Anaconda more efficiently? It works really well in most cases.

https://mamba.readthedocs.io/

Because conda is very slow at resolving dependencies. Mamba (https://github.com/mamba-org/mamba) is faster if that is your goal

use mamba instead

We started using tl::expected in https://github.com/mamba-org/mamba/ since the beginning of this year and some other related projects like https://github.com/mamba-org/powerloader . I don't know much other big open-source codebases that use that specific lib.

Great writeup. Minor comment about the portion of the post mentioning Conda being glacially slow: Mamba [1] is a much better drop-in replacement written in C++. Not only is it significantly faster, but error messages are much more sane and helpful.

That being said, I do agree that Pkg.jl is much more sleek and modern than Conda/Mamba.

[1]: https://github.com/mamba-org/mamba

I thought that python could live a little longer when I learned about mamba. But then I found out it is written in C++? Why write a package manager for a dying language in a language that is almost dead???

Yes, I use Conda enviroments (actually I use Mamba to manage them now).