diff --git a/.github/workflows/pypi.yml b/.github/workflows/CD.yml
similarity index 92%
rename from .github/workflows/pypi.yml
rename to .github/workflows/CD.yml
index fcbaef3..a699a90 100644
--- a/.github/workflows/pypi.yml
+++ b/.github/workflows/CD.yml
@@ -1,4 +1,4 @@
-name: To PyPI
+name: Delivery automation
 
 on:
   push:
@@ -30,7 +30,6 @@ jobs:
 
       - name: Update version in setup.py and lightorch/_version.py
         run: |
-          sed -i "s/{{VERSION_PLACEHOLDER}}/${{ env.TAG_NAME }}/g" setup.py
           sed -i "s/{{VERSION_PLACEHOLDER}}/${{ env.TAG_NAME }}/g" lightorch/_version.py
 
       - name: Build the package
diff --git a/.github/workflows/default.yml b/.github/workflows/CI.yml
similarity index 97%
rename from .github/workflows/default.yml
rename to .github/workflows/CI.yml
index 03fbf4a..a9b77f0 100644
--- a/.github/workflows/default.yml
+++ b/.github/workflows/CI.yml
@@ -1,4 +1,4 @@
-name: Default
+name: Integration automation
 
 on:
   push:
diff --git a/README.md b/README.md
index eaf5753..790bd82 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,8 @@
 [![license](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![code-style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![pypi](https://img.shields.io/pypi/v/lightorch)](https://pypi.org/project/lightorch)
-![CI-CD](https://github.com/Jorgedavyd/LighTorch/actions/workflows/default.yml/badge.svg)
+![CI](https://github.com/Jorgedavyd/LighTorch/actions/workflows/CI.yml/badge.svg)
+![CD](https://github.com/Jorgedavyd/LighTorch/actions/workflows/CD.yml/badge.svg)
 
 # LighTorch
 
diff --git a/lightorch/default/__init__.py b/lightorch/default/__init__.py
deleted file mode 100644
index 5d383ce..0000000
--- a/lightorch/default/__init__.py
+++ /dev/null
@@ -1,3 +0,0 @@
-from .diffusion import *
-from .transformer import *
-from .vae import *
diff --git a/lightorch/default/diffusion.py b/lightorch/default/diffusion.py
deleted file mode 100644
index e69de29..0000000
diff --git a/lightorch/default/transformer.py b/lightorch/default/transformer.py
deleted file mode 100644
index e69de29..0000000
diff --git a/lightorch/default/vae.py b/lightorch/default/vae.py
deleted file mode 100644
index 3da3623..0000000
--- a/lightorch/default/vae.py
+++ /dev/null
@@ -1,101 +0,0 @@
-import torch
-from torch import nn, Tensor
-from typing import Tuple, Sequence
-from ..nn.criterions import _Loss
-from ..training import Module
-from dataclasses import dataclass
-
-"""
-VAE
-
-beta-VAE
-
-Conditional VAE
-"""
-
-
-@dataclass
-class ValidKwargs:
-    optimizer: torch.optim.Optimizer
-    scheduler: torch.optim.lr_scheduler.LRScheduler
-
-    encoder_lr: float
-    encoder_wd: float
-    decoder_lr: float
-    decoder_wd: float
-
-    grad_clip_value: float
-
-    # Reconstruction criterion
-    reconstruction_criterion: nn.Module
-    recons_params: Sequence[float] | float | None
-
-
-class Loss(_Loss):
-    """
-    # Variational Autoencoder Loss:
-    \mathcal{L}_{total} = \mathcal{L}_{recons} - \beta \mathcal{L}_{KL}
-    Given a beta parameter, it is converted into a \beta-VAE.
-    """
-
-    def __init__(self, beta: float, reconstruction_criterion: nn.Module) -> None:
-        super().__init__(
-            reconstruction_criterion.labels.append("KL Divergence"),
-            reconstruction_criterion.factors.update({"KL Divergence": beta}),
-        )
-
-        self.L_recons = reconstruction_criterion(**self.recons_kwargs)
-        self.beta = beta
-
-    def forward(self, I_out, I_gt, mu, logvar) -> Tuple[Tensor, ...]:
-        L_recons = self.L_recons(I_out, I_gt)
-
-        L_kl = -0.5 * torch.sum(torch.log(logvar) - 1 + logvar + torch.pow(mu, 2))
-
-        return (L_recons, L_kl, L_recons + self.beta * L_kl)
-
-
-class VAE(Module):
-    """ """
-
-    def __init__(
-        self,
-        encoder: nn.Module,
-        decoder: nn.Module,
-        conditional: bool = True,
-        **hparams,
-    ) -> None:
-        super().__init__()
-        # Defining the hyperparameters
-        for hparam_name, hparam in hparams.items():
-            setattr(self, hparam_name, hparam)
-        # Defining the encoder-decoder architecture
-        self.encoder = encoder
-        self.decoder = decoder
-        # Defining conditional VAE
-        self.conditional = conditional
-        # Defining the criterion
-        self.criterion = Loss(self.beta, self.reconstruction_criterion)
-        # latent variable characteristics
-        assert (
-            self.encoder.fc.out_features % 2 == 0
-        ), f"Not valid encoder final layer output size {self.encoder.fc.out_features}, should be even."
-        self._half = self.encoder.fc.out_features // 2
-
-    def _reparametrization(self, encoder_output: Tensor) -> Tuple[Tensor, ...]:
-        # encoder_output = encoder_output.view(b, _, 2 * self._half, 2*self._half)
-        pass
-
-    def training_step(self, batch, idx) -> Tensor:
-        x, y = batch
-        x, mu, std = self(x, y)
-        return self.compute_loss(x, mu, std)
-
-    def validation_step(self, batch, idx) -> None:
-        pass
-
-    def forward(self, x: Tensor) -> Tuple[Tensor, ...] | Tensor:
-        x = self.encoder(x)
-        x, mu, std = self._reparametrization(x)
-        x = self.decoder(x)
-        return x, mu, std
diff --git a/setup.py b/setup.py
index af7dc14..769885c 100644
--- a/setup.py
+++ b/setup.py
@@ -1,5 +1,5 @@
 from setuptools import setup, find_packages
-from lightorch import __author__, __email__
+from lightorch import __author__, __email__, __version__
 from pathlib import Path
 
 this_directory = Path(__file__).parent
@@ -8,7 +8,7 @@
 if __name__ == "__main__":
     setup(
         name="lightorch",
-        version='{{VERSION_PLACEHOLDER}}',
+        version=__version__,
         packages=find_packages(),
         author=__author__,
         long_description=long_description,
diff --git a/tests/test_models.py b/tests/test_models.py
deleted file mode 100644
index e69de29..0000000