diff --git a/dl/notebooks/transformer-explainer.py b/dl/notebooks/transformer-explainer.py
new file mode 100644
index 00000000..d65675d1
--- /dev/null
+++ b/dl/notebooks/transformer-explainer.py
@@ -0,0 +1,360 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.15.2
+#   kernelspec:
+#     display_name: .venv
+#     language: python
+#     name: python3
+# ---
+
+# # Transformer Explainer
+
+import math
+
+import matplotlib.pyplot as plt
+import numpy as np
+import scipy as sp
+import torch
+from torch import nn
+
+# ## Examples
+
+x = np.array([1, 3])
+
+qk = np.outer(x, x)
+sp.special.expit(qk)
+
+sp.special.expit(qk).dot(x)
+
+sp.special.expit(np.outer([1, 1], [1, 1]))
+
+# ## The A Matrix
+#
+# Some examples of the A matrix.
+
+x = np.array([1, 10])
+
+
+def compare_a(a, x):
+    return a, sp.special.expit(a), sp.special.expit(a).dot(x)
+
+
+a_1 = np.array([[1, 0], [0, 1]])
+compare_a(a_1, x)
+
+a_2 = np.array([[1, -10], [-10, 1]])
+compare_a(a_2, x)
+
+a_3 = np.array([[-10, 1], [1, -10]])
+compare_a(a_3, x)
+
+# ## Visualize
+#
+# We plot out the q,k vectors and the corresponding attention.
+
+# +
+atten_similarity_q = np.array([[1], [10]])
+atten_similarity_k = np.array([[1], [10]])
+
+atten_similarity_sim = sp.special.expit(
+    np.outer(atten_similarity_q, atten_similarity_k)
+)
+
+
+for a in [atten_similarity_q, atten_similarity_k, atten_similarity_sim]:
+    fig, ax = plt.subplots(figsize=(7, 7))
+
+    ax.matshow(a)
+
+    for (i, j), z in np.ndenumerate(a):
+        ax.text(
+            j,
+            i,
+            "{:0.1f}".format(z),
+            ha="center",
+            va="center",
+            bbox=dict(boxstyle="round", facecolor="white", edgecolor="0.3"),
+            fontsize="xx-large",
+        )
+
+    ax.set_axis_off()
+# -
+
+# ## Positional Encoding
+
+import math
+
+
+# +
+class PositionalEncodingSimple:
+    """Positional encoding for our transformer
+    written in numpy.
+
+    :param d_model: hidden dimension of the encoder
+    :param max_len: maximum length of our positional
+        encoder. The encoder can not encode sequence
+        length longer than max_len.
+    """
+
+    def __init__(self, d_model: int, max_len: int = 100):
+        position = np.expand_dims(np.arange(max_len), axis=1)
+        div_term = np.exp(np.arange(0, d_model, 2) * (-math.log(10000.0) / d_model))
+        self.pe = np.zeros((max_len, d_model))
+        self.pe[:, 0::2] = np.sin(position * div_term)
+        self.pe[:, 1::2] = np.cos(position * div_term)
+
+    def __call__(self, x: np.ndarray) -> np.ndarray:
+        """
+        :param x: input to be encoded
+            with shape
+            `(batch_size, sequence_length, embedding_dim)`
+        """
+        return self.pe[: x.shape[1]]
+
+
+pes = PositionalEncodingSimple(d_model=50)
+x_pes_in = np.ones((1, 10, 1))
+
+x_pes_out = pes(x=x_pes_in)
+
+_, ax = plt.subplots(figsize=(10, 6.18))
+
+ax.matshow(x_pes_out, cmap="cividis")
+ax.set_xlabel("Embedding")
+ax.set_ylabel("Temporal")
+
+# +
+_, ax = plt.subplots()
+
+ax.plot(x_pes_out[-1, :])
+ax.plot(x_pes_out[0, :])
+
+
+# -
+
+# Positional encoding in nixtla
+
+
+class PositionalEmbedding(nn.Module):
+    def __init__(self, hidden_size, max_len=5000):
+        super(PositionalEmbedding, self).__init__()
+        # Compute the positional encodings once in log space.
+        pe = torch.zeros(max_len, hidden_size).float()
+        pe.require_grad = False
+
+        position = torch.arange(0, max_len).float().unsqueeze(1)
+        div_term = (
+            torch.arange(0, hidden_size, 2).float() * -(math.log(10000.0) / hidden_size)
+        ).exp()
+
+        pe[:, 0::2] = torch.sin(position * div_term)
+        pe[:, 1::2] = torch.cos(position * div_term)
+
+        pe = pe.unsqueeze(0)
+        self.register_buffer("pe", pe)
+
+    def forward(self, x):
+        return self.pe[:, : x.size(1)]
+
+
+pe = PositionalEmbedding(hidden_size=192, max_len=20)
+
+plt.plot((torch.arange(0, 192, 2).float() * -(math.log(10000.0) / 192)).exp().numpy())
+
+
+# Token Embedding
+
+
+class TokenEmbedding(nn.Module):
+    def __init__(self, c_in, hidden_size):
+        super(TokenEmbedding, self).__init__()
+        padding = 1 if torch.__version__ >= "1.5.0" else 2
+        self.tokenConv = nn.Conv1d(
+            in_channels=c_in,
+            out_channels=hidden_size,
+            kernel_size=3,
+            padding=padding,
+            padding_mode="circular",
+            bias=False,
+        )
+        for m in self.modules():
+            if isinstance(m, nn.Conv1d):
+                nn.init.kaiming_normal_(
+                    m.weight, mode="fan_in", nonlinearity="leaky_relu"
+                )
+
+    def forward(self, x):
+        x = self.tokenConv(x.permute(0, 2, 1)).transpose(1, 2)
+        return x
+
+
+x_te_in = torch.ones((1, 10, 1))
+
+# +
+te = TokenEmbedding(c_in=1, hidden_size=4)
+
+x_te = te(x_te_in)
+
+x_te.shape
+
+# +
+te_pe = PositionalEmbedding(hidden_size=4, max_len=20)
+
+te_pe(x)
+# -
+
+
+from neuralforecast.common._modules import DataEmbedding
+
+
+# +
+class TriangularCausalMask:
+    def __init__(self, B, L, device="cpu"):
+        mask_shape = [B, 1, L, L]
+        with torch.no_grad():
+            self._mask = torch.triu(
+                torch.ones(mask_shape, dtype=torch.bool), diagonal=1
+            ).to(device)
+
+    @property
+    def mask(self):
+        return self._mask
+
+
+class FullAttention(nn.Module):
+    """
+    FullAttention
+    """
+
+    def __init__(
+        self, mask_flag=True, scale=None, attention_dropout=0.1, output_attention=False
+    ):
+        super(FullAttention, self).__init__()
+        self.scale = scale
+        self.mask_flag = mask_flag
+        self.output_attention = output_attention
+        self.dropout = nn.Dropout(attention_dropout)
+
+    def forward(self, queries, keys, values, attn_mask):
+        B, L, H, E = queries.shape
+        _, S, _, D = values.shape
+        scale = self.scale or 1.0 / math.sqrt(E)
+
+        scores = torch.einsum("blhe,bshe->bhls", queries, keys)
+
+        if self.mask_flag:
+            if attn_mask is None:
+                attn_mask = TriangularCausalMask(B, L, device=queries.device)
+
+            scores.masked_fill_(attn_mask.mask, -np.inf)
+
+        A = self.dropout(torch.softmax(scale * scores, dim=-1))
+        V = torch.einsum("bhls,bshd->blhd", A, values)
+
+        if self.output_attention:
+            return (V.contiguous(), A)
+        else:
+            return (V.contiguous(), None)
+
+
+class AttentionLayer(nn.Module):
+    def __init__(self, attention, hidden_size, n_head, d_keys=None, d_values=None):
+        super(AttentionLayer, self).__init__()
+
+        d_keys = d_keys or (hidden_size // n_head)
+        d_values = d_values or (hidden_size // n_head)
+
+        self.inner_attention = attention
+        self.query_projection = nn.Linear(hidden_size, d_keys * n_head)
+        self.key_projection = nn.Linear(hidden_size, d_keys * n_head)
+        self.value_projection = nn.Linear(hidden_size, d_values * n_head)
+        self.out_projection = nn.Linear(d_values * n_head, hidden_size)
+        self.n_head = n_head
+
+    def forward(self, queries, keys, values, attn_mask):
+        B, L, _ = queries.shape
+        _, S, _ = keys.shape
+        H = self.n_head
+
+        queries = self.query_projection(queries).view(B, L, H, -1)
+        keys = self.key_projection(keys).view(B, S, H, -1)
+        values = self.value_projection(values).view(B, S, H, -1)
+
+        out, attn = self.inner_attention(queries, keys, values, attn_mask)
+        # out = out.view(B, L, -1)
+
+        # return self.out_projection(out), attn
+        return out, attn
+
+
+# +
+enc_in = 1
+hidden_size = 4
+
+enc_embedding = DataEmbedding(
+    c_in=enc_in, exog_input_size=0, hidden_size=hidden_size, pos_embedding=True
+)
+# -
+
+x = torch.ones(size=(1, 10, 1))  # batch size: 1, history length 10, variables 1
+
+x_embedded = enc_embedding(x)
+x_embedded.shape
+
+attention = FullAttention(mask_flag=False, output_attention=True)
+attention_layer = AttentionLayer(
+    attention,
+    hidden_size=hidden_size,
+    n_head=1,
+)
+
+attention_layer.query_projection(x_embedded).view(1, 10, 1, -1).shape
+
+# +
+al_out, al_att = attention_layer(x_embedded, x_embedded, x_embedded, attn_mask=False)
+
+al_out.shape
+
+# +
+queries = attention_layer.query_projection(x_embedded).view(1, 10, 1, -1)
+keys = attention_layer.key_projection(x_embedded).view(1, 10, 1, -1)
+
+torch.einsum("blhe,bshe->bhls", queries, keys).shape
+# -
+
+queries.shape
+
+
+class DataEmbedding_inverted(nn.Module):
+    """
+    DataEmbedding_inverted
+    """
+
+    def __init__(self, c_in, hidden_size, dropout=0.1):
+        super(DataEmbedding_inverted, self).__init__()
+        self.value_embedding = nn.Linear(c_in, hidden_size)
+        self.dropout = nn.Dropout(p=dropout)
+
+    def forward(self, x, x_mark):
+        x = x.permute(0, 2, 1)
+        # x: [Batch Variate Time]
+        if x_mark is None:
+            x = self.value_embedding(x)
+        else:
+            # the potential to take covariates (e.g. timestamps) as tokens
+            x = self.value_embedding(torch.cat([x, x_mark.permute(0, 2, 1)], 1))
+        # x: [Batch Variate hidden_size]
+        return self.dropout(x)
+
+
+# +
+i_de = DataEmbedding_inverted(10, hidden_size)
+
+i_enc_out = i_de(x, None)
+
+i_enc_out.shape
diff --git a/dl/notebooks/transformer-ts-nixtla-testing-m5.py b/dl/notebooks/transformer-ts-nixtla-testing-m5.py
new file mode 100644
index 00000000..0c815835
--- /dev/null
+++ b/dl/notebooks/transformer-ts-nixtla-testing-m5.py
@@ -0,0 +1,427 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.15.2
+#   kernelspec:
+#     display_name: .venv
+#     language: python
+#     name: python3
+# ---
+
+# # Transformer Forecaster with neuralforecast
+
+# +
+import os
+
+os.environ["NIXTLA_ID_AS_COL"] = "1"
+
+import datetime
+from typing import Optional
+
+# +
+import pandas as pd
+
+# +
+from loguru import logger
+
+# -
+
+# ## Load Data
+
+
+data_source = "https://raw.githubusercontent.com/datumorphism/dataset-m5-simplified/b486cd6a3e183b80016a91ba0fd9b19493cdc587/dataset/m5_store_sales.csv"
+
+df = (
+    pd.read_csv(data_source, parse_dates=["date"])
+    .rename(columns={"date": "ds", "CA": "y"})[["ds", "y"]]
+    .assign(unique_id=1)
+)
+# -
+
+df.describe()
+
+# +
+import matplotlib.pyplot as plt
+import seaborn as sns
+from statsmodels.graphics.tsaplots import plot_acf
+
+sns.set_theme(context="paper", style="ticks", palette="colorblind")
+
+
+_, ax = plt.subplots(figsize=(10, 13), nrows=3)
+
+sns.lineplot(df, x="ds", y="y", color="k", ax=ax[0])
+
+ax[0].set_title("Walmart Sales in CA")
+ax[0].set_ylabel("Sales")
+
+sns.lineplot(
+    (df.loc[(df.ds >= "2015-01-01") & (df.ds < "2016-01-01")]),
+    x="ds",
+    y="y",
+    color="k",
+    ax=ax[1],
+)
+
+ax[1].set_title("Walmart Sales in CA in 2015")
+ax[1].set_ylabel("Sales")
+
+plot_acf(df.y, ax=ax[2], color="k")
+# -
+
+# ## Prepare Data
+
+df.ds.max(), df.ds.min()
+
+# +
+train_test_split_date = "2016-01-01"
+
+df_train = df[df.ds < train_test_split_date]
+df_test = df[(df.ds >= train_test_split_date)]
+
+horizon = 3
+horizon
+# -
+
+# ## Baselines
+
+from statsforecast import StatsForecast
+from statsforecast.arima import arima_string
+from statsforecast.models import AutoARIMA
+
+sf = StatsForecast(
+    models=[
+        AutoARIMA(
+            # season_length = 365.25
+            seasonal=False
+        )
+    ],
+    freq="d",
+)
+
+sf.fit(df_train)
+
+
+def forecast_test(
+    forecaster_pred: callable,
+    df_train: pd.DataFrame,
+    df_test: pd.DataFrame,
+) -> pd.DataFrame:
+    """Generate forecasts for tests
+
+    :param forecaster_pred: forecasting function/method
+    :param df_train: train dataframe
+    :param df_test: test dataframe
+    """
+    dfs_pred = []
+    for i in range(len(df_test)):
+        logger.debug(f"Prediction Step: {i}")
+        df_pred_input_i = pd.concat([df_train, df_test[:i]]).reset_index(drop=True)
+        df_pred_output_i = forecaster_pred(df_pred_input_i)
+        df_pred_output_i["step"] = i
+        dfs_pred.append(df_pred_output_i)
+    df_y_hat = pd.concat(dfs_pred)
+
+    return df_y_hat
+
+
+def visualize_predictions(
+    df_train: pd.DataFrame,
+    df_test: pd.DataFrame,
+    df_pred: pd.DataFrame,
+    model_name: str,
+    n_ahead: Optional[int] = None,
+    title: Optional[str] = None,
+    ax: Optional[plt.axes] = None,
+) -> None:
+    """
+    Visualizes the forecasts
+
+    :param df_train: train dataframe
+    :param df_test: test dataframe
+    :param df_pred: prediction dataframe
+    :param model_name: which model to visualize
+    :param n_ahead: which future step to visualze
+    :param title: title of the chart
+    :param ax: matplotlib axes
+    """
+    if ax is None:
+        _, ax = plt.subplots(figsize=(10, 6.18))
+
+    sns.lineplot(df_train, x="ds", y="y", ax=ax)
+
+    sns.lineplot(df_test, x="ds", y="y", color="k", ax=ax)
+
+    if n_ahead is None:
+        sns.lineplot(
+            df_pred, x="ds", y=model_name, hue="step", linestyle="dashed", ax=ax
+        )
+    else:
+        dfs_pred_n_ahead = []
+        for i in df_pred.step.unique():
+            dfs_pred_n_ahead.append(
+                df_pred.loc[df_pred.step == i].iloc[n_ahead - 1 : n_ahead]
+            )
+        df_pred_n_ahead = pd.concat(dfs_pred_n_ahead)
+        sns.lineplot(df_pred_n_ahead, x="ds", y=model_name, linestyle="dashed", ax=ax)
+
+    ax.set_title("Sales Forecast" if title is None else title)
+    ax.set_ylabel("Sales")
+    ax.set_xlabel("Date")
+    # ax.legend(prop={'size': 15})
+    # ax.grid()
+
+
+# +
+df_y_hat_arima = forecast_test(
+    lambda x: sf.forecast(df=x, h=horizon), df_train=df_train, df_test=df_test
+)
+
+df_y_hat_arima
+# -
+
+visualize_predictions(
+    df_train=df_train, df_test=df_test, df_pred=df_y_hat_arima, model_name="AutoARIMA"
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds > "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_arima,
+    model_name="AutoARIMA",
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds > "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_arima,
+    model_name="AutoARIMA",
+    n_ahead=1,
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds > "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_arima,
+    model_name="AutoARIMA",
+    n_ahead=2,
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds > "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_arima,
+    model_name="AutoARIMA",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (ARIMA)",
+)
+
+arima_string(sf.fitted_[0, 0].model_)
+
+# ## Transformers
+
+from neuralforecast import NeuralForecast
+from neuralforecast.models import VanillaTransformer, iTransformer
+
+models = [
+    VanillaTransformer(
+        hidden_size=128,
+        n_head=4,
+        learning_rate=0.0001,
+        scaler_type="robust",
+        max_steps=500,
+        batch_size=32,
+        windows_batch_size=512,
+        random_seed=16,
+        input_size=30,
+        step_size=3,
+        h=horizon,
+        # **{'hidden_size': 128,
+        #     'n_head': 4,
+        #     'learning_rate': 0.00010614524276500768,
+        #     'scaler_type': 'robust',
+        #     'max_steps': 500,
+        #     'batch_size': 32,
+        #     'windows_batch_size': 512,
+        #     'random_seed': 16,
+        #     'input_size': 30,
+        #     'step_size': 3,
+        #     "h": horizon,
+        # }
+    ),
+    iTransformer(
+        input_size=30,
+        h=horizon,
+        max_steps=50,
+        n_series=1,
+    ),
+]
+nf = NeuralForecast(models=models, freq="d")
+
+nf.fit(df=df_train)
+
+df_y_hat_transformer = forecast_test(nf.predict, df_train=df_train, df_test=df_test)
+
+df_y_hat_transformer
+
+df_test
+
+df_y_hat_transformer.ds.dt.freq
+
+visualize_predictions(
+    df_train=df_train,
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="VanillaTransformer",
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="VanillaTransformer",
+    n_ahead=1,
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="VanillaTransformer",
+    n_ahead=2,
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="VanillaTransformer",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (VanillaTransformer)",
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="iTransformer",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (iTransformer)",
+)
+
+# ## Evaluations
+
+from datasetsforecast.evaluation import accuracy
+from datasetsforecast.losses import mae, mape, mse, rmse, smape
+
+df_y_hat_transformer.loc[df_y_hat_transformer.step == 0]
+
+df_test
+
+df_y_hat_transformer.loc[df_y_hat_transformer.step == 0]
+
+# +
+transformer_evals = []
+
+for s in df_y_hat_transformer.step.unique():
+    df_transformer_eval_s = accuracy(
+        Y_hat_df=df_y_hat_transformer.loc[df_y_hat_transformer.step == s],
+        Y_test_df=df_test,
+        Y_df=df_train,
+        metrics=[mse, mae, rmse],
+        # agg_by=['unique_id']
+    )
+    df_transformer_eval_s["step"] = s
+    transformer_evals.append(df_transformer_eval_s)
+
+df_transformer_eval = pd.concat(transformer_evals)
+
+df_transformer_eval.head()
+
+# +
+baseline_evals = []
+
+for s in df_y_hat_arima.step.unique():
+    df_baseline_eval_s = accuracy(
+        Y_hat_df=df_y_hat_arima.loc[df_y_hat_arima.step == s],
+        Y_test_df=df_test,
+        Y_df=df_train,
+        metrics=[mse, mae, rmse],
+        # agg_by=['unique_id']
+    )
+    df_baseline_eval_s["step"] = s
+    baseline_evals.append(df_baseline_eval_s)
+
+
+df_baseline_eval = pd.concat(baseline_evals)
+
+df_baseline_eval.head()
+
+
+# +
+df_eval_metrics = pd.merge(
+    df_transformer_eval, df_baseline_eval, how="left", on=["metric", "step"]
+).melt(
+    id_vars=["metric", "step"],
+    value_vars=[
+        "VanillaTransformer",
+        "iTransformer",
+        "AutoARIMA",
+    ],
+    var_name="model",
+)
+
+df_eval_metrics
+
+# +
+_, ax = plt.subplots(figsize=(13, 5), ncols=3)
+
+for i, m in enumerate(df_eval_metrics.metric.unique()):
+    sns.violinplot(
+        df_eval_metrics.loc[df_eval_metrics.metric == m],
+        x="model",
+        y="value",
+        hue="model",
+        fill=False,
+        ax=ax[i],
+        label=m,
+    )
+    ax[i].set_title(f"Metric: {m}")
+
+# +
+_, ax = plt.subplots(figsize=(10, 13), nrows=3)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds > "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_arima,
+    model_name="AutoARIMA",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (ARIMA)",
+    ax=ax[0],
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="VanillaTransformer",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (VanillaTransformer)",
+    ax=ax[1],
+)
+
+visualize_predictions(
+    df_train=df_train.loc[df_train.ds >= "2015-01-01"],
+    df_test=df_test,
+    df_pred=df_y_hat_transformer,
+    model_name="iTransformer",
+    n_ahead=3,
+    title="Forecasting 3 Steps Ahead (iTransformer)",
+    ax=ax[2],
+)
+# -
diff --git a/dl/notebooks/transformer-ts-nixtla-testing.py b/dl/notebooks/transformer-ts-nixtla-testing.py
new file mode 100644
index 00000000..17bc656e
--- /dev/null
+++ b/dl/notebooks/transformer-ts-nixtla-testing.py
@@ -0,0 +1,229 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.15.2
+#   kernelspec:
+#     display_name: .venv
+#     language: python
+#     name: python3
+# ---
+
+# # Transformer Forecaster with neuralforecast
+
+import matplotlib.pyplot as plt
+
+# +
+import pandas as pd
+import seaborn as sns
+
+sns.set_theme(context="paper", style="ticks", palette="colorblind")
+# -
+
+# ## Load Data
+
+# +
+data_source = "https://gist.githubusercontent.com/emptymalei/15e548f483e896be0afc99e49dd6fbc9/raw/8384d82cdaaed4d9b0a555888efb70d79911dd2a/sunspot_nixtla.csv"
+
+df = pd.read_csv(data_source, parse_dates=["ds"])
+
+# -
+
+df.describe()
+
+# +
+_, ax = plt.subplots()
+sns.lineplot(df, x="ds", y="y", ax=ax)
+
+ax.set_title("Sunspot Time Series")
+ax.set_ylabel("Sunspot Number")
+# -
+
+# ## Prepare Data
+
+# +
+train_test_split_date = "2000-01-01"
+
+df_train = df[df.ds <= train_test_split_date]
+df_test = df[df.ds > train_test_split_date]
+
+horizon = 3
+horizon
+# -
+
+# ## Baselines
+
+from statsforecast import StatsForecast
+from statsforecast.models import AutoARIMA
+
+sf = StatsForecast(models=[AutoARIMA(season_length=12)], freq="YS")
+
+sf.fit(df_train)
+
+
+def forecast_test(forecaster_pred, df_train, df_test):
+    dfs_pred = []
+    for i in range(len(df_test)):
+        df_pred_input_i = pd.concat([df_train, df_test[:i]])
+        print(df_pred_input_i.ds.max())
+        df_pred_output_i = forecaster_pred(df_pred_input_i)
+        df_pred_output_i["step"] = i
+        dfs_pred.append(df_pred_output_i)
+    df_y_hat = pd.concat(dfs_pred).reset_index(drop=False)
+    return df_y_hat
+
+
+def visualize_predictions(
+    df_train: pd.DataFrame,
+    df_test: pd.DataFrame,
+    df_pred: pd.DataFrame,
+    model_name: str,
+):
+    _, ax = plt.subplots()
+
+    sns.lineplot(df_train, x="ds", y="y", ax=ax)
+
+    sns.lineplot(df_test, x="ds", y="y", color="k", ax=ax)
+
+    sns.lineplot(df_pred, x="ds", y=model_name, hue="step", ax=ax)
+
+    ax.set_title("Sunspot Forecast", fontsize=22)
+    ax.set_ylabel("Sunspot Number", fontsize=20)
+    ax.set_xlabel("Year", fontsize=20)
+    ax.legend(prop={"size": 15})
+    ax.grid()
+
+
+df_y_hat_arima = forecast_test(
+    lambda x: sf.predict(h=horizon, level=[95]), df_train=df_train, df_test=df_test
+)
+
+visualize_predictions(
+    df_train=df_train, df_test=df_test, df_pred=df_y_hat_arima, model_name="AutoARIMA"
+)
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+df_chart = df_test.merge(df_y_hat_arima, how="left", on=["unique_id", "ds"])
+df_chart = pd.concat([df_train, df_chart]).set_index("ds")
+
+df_chart[
+    [
+        "y",
+        "AutoARIMA",
+        # 'NHITS'
+    ]
+].plot(ax=ax, linewidth=2)
+
+ax.set_title("AirPassengers Forecast", fontsize=22)
+ax.set_ylabel("Monthly Passengers", fontsize=20)
+ax.set_xlabel("Timestamp [t]", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
+# -
+
+# ## Transformers
+
+from neuralforecast import NeuralForecast
+from neuralforecast.models import NBEATS, NHITS, VanillaTransformer, iTransformer
+
+models = [
+    VanillaTransformer(
+        # input_size=9, h=horizon,
+        # n_head=4,
+        # windows_batch_size=512,
+        # learning_rate=0.00010614524276500768,
+        # # conv_hidden_size=2,
+        # # encoder_layers=6,
+        # max_steps=500,
+        # #early_stop_patience_steps=5,
+        **{
+            "hidden_size": 128,
+            "n_head": 4,
+            "learning_rate": 0.00010614524276500768,
+            "scaler_type": "robust",
+            "max_steps": 500,
+            "batch_size": 32,
+            "windows_batch_size": 512,
+            "random_seed": 16,
+            "input_size": 30,
+            "step_size": 3,
+            "h": horizon,
+        }
+    ),
+    # iTransformer(
+    #     input_size=history_length, h=horizon,
+    #     # n_head=1,
+    #     # conv_hidden_size=1,
+    #     # encoder_layers=6,
+    #     max_steps=50,
+    #     n_series=1,
+    #     #early_stop_patience_steps=5,
+    # ),
+    # NBEATS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #        ),
+    # NHITS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #       )
+]
+nf = NeuralForecast(models=models, freq="YS")
+
+nf.fit(df=df_train)
+
+train_test_split_date
+
+
+dfs_pred = []
+for i in range(len(df_test)):
+    df_pred_input_i = pd.concat([df_train, df_test[:i]])
+    df_pred_output_i = nf.predict(df_pred_input_i)
+    df_pred_output_i["step"] = i
+    dfs_pred.append(df_pred_output_i)
+df_y_hat = pd.concat(dfs_pred).reset_index(drop=False)
+
+df_y_hat
+
+df_test
+
+df_y_hat.ds.dt.freq
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+
+sns.lineplot(df_train, x="ds", y="y", ax=ax)
+
+sns.lineplot(df_test, x="ds", y="y", color="k", ax=ax)
+
+sns.lineplot(df_y_hat, x="ds", y="VanillaTransformer", hue="step", ax=ax)
+
+
+ax.set_title("Sunspot Forecast", fontsize=22)
+ax.set_ylabel("Avg Sunspot Area", fontsize=20)
+ax.set_xlabel("Year", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
+# -
+
+from datasetsforecast.evaluation import accuracy
+from datasetsforecast.losses import mae, mse, rmse
+
+df_y_hat.loc[df_y_hat.step == 0]
+
+df_test
+
+# +
+evaluation_df = accuracy(
+    Y_hat_df=df_y_hat.loc[df_y_hat.step == 0],
+    Y_test_df=df_test,
+    Y_df=df_train,
+    metrics=[mse, mae, rmse],
+    agg_by=["unique_id"],
+)
+
+evaluation_df.head()
diff --git a/dl/notebooks/transformer-ts-nixtla.py b/dl/notebooks/transformer-ts-nixtla.py
new file mode 100644
index 00000000..61a614f9
--- /dev/null
+++ b/dl/notebooks/transformer-ts-nixtla.py
@@ -0,0 +1,230 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.15.2
+#   kernelspec:
+#     display_name: .venv
+#     language: python
+#     name: python3
+# ---
+
+# # Transformer Forecaster with neuralforecast
+
+import pandas as pd
+import seaborn as sns
+
+# ## Load Data
+
+# +
+data_source = "https://gist.githubusercontent.com/emptymalei/921a624ce44e6a60bb6ec637b195ceaf/raw/4cb52fa20dcc598e16891eae2749fd96a97750e9/sunspot.csv"
+
+df = (
+    pd.read_csv(data_source, parse_dates=["date"])
+    .rename(columns={"date": "ds", "avg_sunspot_area": "y"})
+    .assign(unique_id=1)
+)
+
+# -
+
+df.describe()
+
+df.plot(x="ds", y="y")
+
+# ## Prepare Data
+
+# +
+train_test_split_date = "2000-01-01"
+
+df_train = df[df.ds <= train_test_split_date]
+df_test = df[df.ds > train_test_split_date]
+
+horizon = 3
+horizon
+# -
+
+# ## Baselines
+
+from statsforecast import StatsForecast
+from statsforecast.models import AutoARIMA
+
+sf = StatsForecast(models=[AutoARIMA(season_length=12)], freq="YS")
+
+sf.fit(df_train)
+
+df_y_hat_arima = sf.predict(h=horizon, level=[95])
+df_y_hat_arima
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+df_chart = df_test.merge(df_y_hat_arima, how="left", on=["unique_id", "ds"])
+df_chart = pd.concat([df_train, df_chart]).set_index("ds")
+
+df_chart[
+    [
+        "y",
+        "AutoARIMA",
+        # 'NHITS'
+    ]
+].plot(ax=ax, linewidth=2)
+
+ax.set_title("AirPassengers Forecast", fontsize=22)
+ax.set_ylabel("Monthly Passengers", fontsize=20)
+ax.set_xlabel("Timestamp [t]", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
+# -
+
+# ## Transformers
+
+from neuralforecast import NeuralForecast
+from neuralforecast.auto import AutoVanillaTransformer
+from neuralforecast.models import NBEATS, NHITS, VanillaTransformer, iTransformer
+
+# +
+# vt_config = dict(
+#     max_steps=1, val_check_steps=1, input_size=12, hidden_size=8
+# )
+auto_vt_model = AutoVanillaTransformer(h=horizon, backend="optuna")
+
+nf_auto = NeuralForecast(models=[auto_vt_model], freq="YS")
+# -
+
+nf_auto.fit(df=df_train, val_size=3)
+
+results = nf_auto.models[0].results.trials_dataframe()
+results.drop(columns="user_attrs_ALL_PARAMS")
+
+
+df_y_hat_optuna = nf_auto.predict().reset_index()
+df_y_hat_optuna.head()
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+df_chart = df_test.merge(df_y_hat_optuna, how="left", on=["unique_id", "ds"])
+df_chart = pd.concat([df_train, df_chart]).set_index("ds")
+
+df_chart[
+    [
+        "y",
+        "AutoVanillaTransformer",
+    ]
+].plot(ax=ax, linewidth=2)
+
+ax.set_title("Forecast", fontsize=22)
+ax.set_ylabel("Sunspot Area", fontsize=20)
+ax.set_xlabel("Timestamp [t]", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
+# -
+
+nf_auto.models[0].results.best_trial.params
+
+# +
+# nf_auto.save("lightning_logs/nf_auto_vanilla_transformer_sunspot")
+# -
+
+# ## Transformers
+
+models = [
+    VanillaTransformer(
+        # input_size=9, h=horizon,
+        # n_head=4,
+        # windows_batch_size=512,
+        # learning_rate=0.00010614524276500768,
+        # # conv_hidden_size=2,
+        # # encoder_layers=6,
+        # max_steps=500,
+        # #early_stop_patience_steps=5,
+        **{
+            "hidden_size": 128,
+            "n_head": 4,
+            "learning_rate": 0.00010614524276500768,
+            "scaler_type": "robust",
+            "max_steps": 500,
+            "batch_size": 32,
+            "windows_batch_size": 512,
+            "random_seed": 16,
+            "input_size": 30,
+            "step_size": 3,
+            "h": horizon,
+        }
+    ),
+    # iTransformer(
+    #     input_size=history_length, h=horizon,
+    #     # n_head=1,
+    #     # conv_hidden_size=1,
+    #     # encoder_layers=6,
+    #     max_steps=50,
+    #     n_series=1,
+    #     #early_stop_patience_steps=5,
+    # ),
+    # NBEATS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #        ),
+    # NHITS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #       )
+]
+nf = NeuralForecast(models=models, freq="YS")
+
+nf.fit(df=df_train)
+
+train_test_split_date
+
+
+dfs_pred = []
+for i in range(len(df_test)):
+    df_pred_input_i = pd.concat([df_train, df_test[:i]])
+    df_pred_output_i = nf.predict(df_pred_input_i)
+    df_pred_output_i["step"] = i
+    dfs_pred.append(df_pred_output_i)
+df_y_hat = pd.concat(dfs_pred).reset_index(drop=False)
+
+df_y_hat
+
+df_test
+
+df_y_hat.ds.dt.freq
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+
+sns.lineplot(df_train, x="ds", y="y", ax=ax)
+
+sns.lineplot(df_test, x="ds", y="y", color="k", ax=ax)
+
+sns.lineplot(df_y_hat, x="ds", y="VanillaTransformer", hue="step", ax=ax)
+
+
+ax.set_title("Sunspot Forecast", fontsize=22)
+ax.set_ylabel("Avg Sunspot Area", fontsize=20)
+ax.set_xlabel("Year", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
+# -
+
+from datasetsforecast.evaluation import accuracy
+from datasetsforecast.losses import mae, mse, rmse
+
+df_y_hat.loc[df_y_hat.step == 0]
+
+df_test
+
+# +
+evaluation_df = accuracy(
+    Y_hat_df=df_y_hat.loc[df_y_hat.step == 0],
+    Y_test_df=df_test,
+    Y_df=df_train,
+    metrics=[mse, mae, rmse],
+    agg_by=["unique_id"],
+)
+
+evaluation_df.head()
diff --git a/dl/notebooks/transformer-ts-nixtla_naive_data.py b/dl/notebooks/transformer-ts-nixtla_naive_data.py
new file mode 100644
index 00000000..55fed854
--- /dev/null
+++ b/dl/notebooks/transformer-ts-nixtla_naive_data.py
@@ -0,0 +1,127 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: light
+#       format_version: '1.5'
+#       jupytext_version: 1.15.2
+#   kernelspec:
+#     display_name: .venv
+#     language: python
+#     name: python3
+# ---
+
+# # Transformer Forecaster with neuralforecast
+
+import pandas as pd
+from ts_dl_utils.datasets.pendulum import Pendulum
+
+# ## Load Data
+
+# +
+pen = Pendulum(length=100)
+df_pen = (
+    pd.DataFrame(pen(10, 400, initial_angle=1, beta=0.00001))
+    .reset_index()
+    .rename(columns={"index": "ds", "theta": "y"})[["ds", "y"]]
+)
+df_pen["unique_id"] = 1
+
+df_pen.head()
+# -
+
+df_pen.plot(x="ds", y="y")
+
+# +
+df_pen_train = df_pen[:-3]
+df_pen_test = df_pen[-3:]
+
+horizon_pen = len(df_pen_test)
+# -
+
+# ## Prepare Data
+
+# ## Baselines
+
+from statsforecast import StatsForecast
+from statsforecast.models import AutoARIMA
+
+sf_pen = StatsForecast(models=[AutoARIMA(season_length=12)], freq=1)
+
+sf_pen.fit(df_pen_train)
+
+df_pen_y_hat_arima = sf_pen.predict(h=horizon_pen, level=[95])
+df_pen_y_hat_arima
+
+# +
+_, ax = plt.subplots()
+
+df_pen_test.plot(x="ds", y="y", ax=ax)
+df_pen_y_hat_arima.plot(x="ds", y="AutoARIMA", ax=ax)
+# -
+
+
+# ## Transformers
+
+# +
+from neuralforecast import NeuralForecast
+from neuralforecast.auto import AutoVanillaTransformer
+from neuralforecast.models import NBEATS, NHITS, VanillaTransformer, iTransformer
+
+history_length_pen = 10
+
+# -
+
+models_pen = [
+    VanillaTransformer(
+        input_size=history_length_pen,
+        h=horizon_pen,
+        n_head=1,
+        conv_hidden_size=1,
+        encoder_layers=6,
+        max_steps=100,
+        # early_stop_patience_steps=5,
+    ),
+    # iTransformer(
+    #     input_size=history_length, h=horizon,
+    #     # n_head=1,
+    #     # conv_hidden_size=1,
+    #     # encoder_layers=6,
+    #     max_steps=50,
+    #     n_series=1,
+    #     #early_stop_patience_steps=5,
+    # ),
+    # NBEATS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #        ),
+    # NHITS(input_size=history_length, h=horizon, max_steps=100, #early_stop_patience_steps=5
+    #       )
+]
+nf_pen = NeuralForecast(models=models_pen, freq=1)
+
+nf_pen.fit(df=df_pen_train)
+
+df_pen_y_hat = nf_pen.predict().reset_index()
+
+# +
+import matplotlib.pyplot as plt
+
+fig, ax = plt.subplots(1, 1, figsize=(20, 7))
+df_chart = df_pen_test.merge(df_pen_y_hat, how="left", on=["unique_id", "ds"])
+df_chart = pd.concat([df_pen_train, df_chart]).set_index("ds")
+
+df_chart[
+    [
+        "y",
+        # 'NBEATS',
+        "VanillaTransformer",
+        # "iTransformer"
+        # 'NHITS'
+    ]
+].plot(ax=ax, linewidth=2)
+
+ax.set_title("AirPassengers Forecast", fontsize=22)
+ax.set_ylabel("Monthly Passengers", fontsize=20)
+ax.set_xlabel("Timestamp [t]", fontsize=20)
+ax.legend(prop={"size": 15})
+ax.grid()
diff --git a/dl/notebooks/transformer_timeseries_univariate.py b/dl/notebooks/transformer_timeseries_univariate.py
index 303ca7bd..6ca68aa4 100644
--- a/dl/notebooks/transformer_timeseries_univariate.py
+++ b/dl/notebooks/transformer_timeseries_univariate.py
@@ -8,9 +8,9 @@
 #       format_version: '1.5'
 #       jupytext_version: 1.15.2
 #   kernelspec:
-#     display_name: deep-learning
+#     display_name: .venv
 #     language: python
-#     name: deep-learning
+#     name: python3
 # ---
 
 # # Transformer for Univariate Time Series Forecasting
@@ -21,8 +21,6 @@
 
 # +
 import math
-from functools import cached_property
-from typing import Dict, List, Tuple
 
 import lightning as L
 import matplotlib.pyplot as plt
@@ -30,9 +28,7 @@
 import pandas as pd
 import torch
 from lightning.pytorch.callbacks.early_stopping import EarlyStopping
-from loguru import logger
 from torch import nn
-from torch.utils.data import DataLoader, Dataset
 from ts_dl_utils.datasets.pendulum import Pendulum, PendulumDataModule
 from ts_dl_utils.evaluation.evaluator import Evaluator
 from ts_dl_utils.naive_forecasters.last_observation import LastObservationForecaster
@@ -58,9 +54,9 @@
 # and $g$ being the surface gravity.
 
 
-pen = Pendulum(length=100)
+pen = Pendulum(length=10000)
 
-df = pd.DataFrame(pen(10, 400, initial_angle=1, beta=0.001))
+df = pd.DataFrame(pen(100, 400, initial_angle=1, beta=0.000001))
 
 # Since the damping constant is very small, the data generated is mostly a sin wave.
 
@@ -82,7 +78,9 @@
 # +
 @dataclasses.dataclass
 class TSTransformerParams:
-    """A dataclass to be served as our parameters for the model."""
+    """A dataclass that contains all
+    the parameters for the transformer model.
+    """
 
     d_model: int = 512
     nhead: int = 8
@@ -91,13 +89,24 @@ class TSTransformerParams:
 
 
 class PositionalEncoding(nn.Module):
-    """Positional encoding for our transformer.
-
-    We borrowed it from https://pytorch.org/tutorials/beginner/transformer_tutorial.html
+    """Positional encoding to be added to
+    input embedding.
+
+    :param d_model: hidden dimension of the encoder
+    :param dropout: rate of dropout
+    :param max_len: maximum length of our positional
+        encoder. The encoder can not encode sequence
+        length longer than max_len.
     """
 
-    def __init__(self, d_model: int, dropout: float = 0.1, max_len: int = 5000):
+    def __init__(
+        self,
+        d_model: int,
+        dropout: float = 0.1,
+        max_len: int = 5000,
+    ):
         super().__init__()
+        self.max_len = max_len
         self.dropout = nn.Dropout(p=dropout)
 
         position = torch.arange(max_len).unsqueeze(1)
@@ -111,9 +120,12 @@ def __init__(self, d_model: int, dropout: float = 0.1, max_len: int = 5000):
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
         """
-        :param x: Tensor, shape `[seq_len, batch_size, embedding_dim]`
+        :param x: input embedded time series,
+            shape `[batch_size, seq_len, embedding_dim]`
         """
-        x = x + self.pe[: x.size(0)]
+        history_length = x.size(1)
+        x = x + self.pe[:history_length]
+
         return self.dropout(x)
 
 
@@ -122,21 +134,25 @@ class TSTransformer(nn.Module):
 
     :param history_length: the length of the input history.
     :param horizon: the number of steps to be forecasted.
-    :param transformer_params: the parameters for the transformer.
+    :param transformer_params: all the parameters.
     """
 
     def __init__(
-        self, history_length: int, horizon: int, transformer_params: TSTransformerParams
+        self,
+        history_length: int,
+        horizon: int,
+        transformer_params: TSTransformerParams,
     ):
         super().__init__()
         self.transformer_params = transformer_params
         self.history_length = history_length
         self.horizon = horizon
 
-        self.regulate_input = nn.Linear(
-            self.history_length, self.transformer_params.d_model
+        self.embedding = nn.Linear(1, self.transformer_params.d_model)
+
+        self.positional_encoding = PositionalEncoding(
+            d_model=self.transformer_params.d_model
         )
-        self.regulate_output = nn.Linear(self.transformer_params.d_model, self.horizon)
 
         encoder_layer = nn.TransformerEncoderLayer(
             d_model=self.transformer_params.d_model,
@@ -147,16 +163,28 @@ def __init__(
             encoder_layer, num_layers=self.transformer_params.num_encoder_layers
         )
 
+        self.reverse_embedding = nn.Linear(self.transformer_params.d_model, 1)
+
+        self.decoder = nn.Linear(self.history_length, self.horizon)
+
     @property
-    def transformer_config(self):
+    def transformer_config(self) -> dict:
+        """all the param in dict format"""
         return dataclasses.asdict(self.transformer_params)
 
     def forward(self, x: torch.Tensor) -> torch.Tensor:
-        x = self.regulate_input(x)
+        """
+        :param x: input historical time series,
+            shape `[batch_size, seq_len, n_var]`
+        """
+        x = self.embedding(x)
+        x = self.positional_encoding(x)
 
         encoder_state = self.encoder(x)
 
-        return self.regulate_output(encoder_state)
+        decoder_in = self.reverse_embedding(encoder_state).squeeze(-1)
+
+        return self.decoder(decoder_in)
 
 
 # -
@@ -171,7 +199,7 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
 history_length_1_step = 100
 horizon_1_step = 1
 
-gap = 10
+gap = 0
 # -
 
 
@@ -182,17 +210,23 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
 
 
 class TransformerForecaster(L.LightningModule):
+    """Transformer forecasting training, validation,
+    and prediction all collected in one class.
+
+    :param transformer: pre-defined transformer model
+    """
+
     def __init__(self, transformer: nn.Module):
         super().__init__()
         self.transformer = transformer
 
-    def configure_optimizers(self):
+    def configure_optimizers(self) -> torch.optim.Optimizer:
         optimizer = torch.optim.SGD(self.parameters(), lr=1e-3)
+
         return optimizer
 
-    def training_step(self, batch, batch_idx):
+    def training_step(self, batch: tuple[torch.Tensor], batch_idx: int) -> torch.Tensor:
         x, y = batch
-        x = x.squeeze(-1).type(self.dtype)
         y = y.squeeze(-1).type(self.dtype)
 
         y_hat = self.transformer(x)
@@ -201,27 +235,30 @@ def training_step(self, batch, batch_idx):
         self.log_dict({"train_loss": loss}, prog_bar=True)
         return loss
 
-    def validation_step(self, batch, batch_idx):
+    def validation_step(
+        self, batch: tuple[torch.Tensor], batch_idx: int
+    ) -> torch.Tensor:
         x, y = batch
-        x = x.squeeze(-1).type(self.dtype)
         y = y.squeeze(-1).type(self.dtype)
 
         y_hat = self.transformer(x)
 
         loss = nn.functional.mse_loss(y_hat, y)
         self.log_dict({"val_loss": loss}, prog_bar=True)
+
         return loss
 
-    def predict_step(self, batch, batch_idx):
+    def predict_step(
+        self, batch: list[torch.Tensor], batch_idx: int
+    ) -> tuple[torch.Tensor]:
         x, y = batch
-        x = x.squeeze(-1).type(self.dtype)
         y = y.squeeze(-1).type(self.dtype)
 
         y_hat = self.transformer(x)
+
         return x, y_hat
 
-    def forward(self, x):
-        x = x.squeeze(-1).type(self.dtype)
+    def forward(self, x: torch.Tensor) -> tuple[torch.Tensor]:
         return x, self.transformer(x)
 
 
@@ -250,10 +287,13 @@ def forward(self, x):
 )
 
 ts_transformer_1_step
-# -
 
+# +
 transformer_forecaster_1_step = TransformerForecaster(transformer=ts_transformer_1_step)
 
+transformer_forecaster_1_step
+# -
+
 # #### Trainer
 
 # +
@@ -275,6 +315,19 @@ def forward(self, x):
 
 # #### Fitting
 
+demo_x = list(pdm_1_step.train_dataloader())[0][0].type(
+    transformer_forecaster_1_step.dtype
+)
+demo_x.shape
+
+nn.Linear(
+    1,
+    ts_transformer_1_step.transformer_params.d_model,
+    dtype=transformer_forecaster_1_step.dtype,
+)(demo_x).shape
+
+ts_transformer_1_step.encoder(ts_transformer_1_step.embedding(demo_x)).shape
+
 trainer_1_step.fit(model=transformer_forecaster_1_step, datamodule=pdm_1_step)
 
 # #### Retrieving Predictions
@@ -299,7 +352,7 @@ def forward(self, x):
 evaluator_1_step = Evaluator(step=0)
 
 # +
-fig, ax = plt.subplots(figsize=(10, 6.18))
+fig, ax = plt.subplots(figsize=(50, 6.18))
 
 ax.plot(
     evaluator_1_step.y_true(dataloader=pdm_1_step.predict_dataloader()),
@@ -311,14 +364,48 @@ def forward(self, x):
 
 ax.plot(evaluator_1_step.y(lobs_1_step_predictions), "b-.", label="naive predictions")
 
+plt.legend()
+
+# +
+fig, ax = plt.subplots(figsize=(10, 6.18))
+
+inspection_slice_length = 200
+
+ax.plot(
+    evaluator_1_step.y_true(dataloader=pdm_1_step.predict_dataloader())[
+        :inspection_slice_length
+    ],
+    "g-",
+    label="truth",
+)
+
+ax.plot(
+    evaluator_1_step.y(predictions_1_step)[:inspection_slice_length],
+    "r--",
+    label="predictions",
+)
+
+ax.plot(
+    evaluator_1_step.y(lobs_1_step_predictions)[:inspection_slice_length],
+    "b-.",
+    label="naive predictions",
+)
+
 plt.legend()
 # -
 
 # To quantify the results, we compute a few metrics.
 
-evaluator_1_step.metrics(predictions_1_step, pdm_1_step.predict_dataloader())
+pd.merge(
+    evaluator_1_step.metrics(predictions_1_step, pdm_1_step.predict_dataloader()),
+    evaluator_1_step.metrics(lobs_1_step_predictions, pdm_1_step.predict_dataloader()),
+    how="left",
+    left_index=True,
+    right_index=True,
+    suffixes=["_transformer", "_naive"],
+)
 
-evaluator_1_step.metrics(lobs_1_step_predictions, pdm_1_step.predict_dataloader())
+# Here SMAPE is better because of better forecasts for larger values
 
 # ## Forecasting (horizon=3)
 
diff --git a/poetry.lock b/poetry.lock
index 97908c3c..3c93e420 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -147,6 +147,25 @@ files = [
 [package.dependencies]
 frozenlist = ">=1.1.0"
 
+[[package]]
+name = "alembic"
+version = "1.13.2"
+description = "A database migration tool for SQLAlchemy."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "alembic-1.13.2-py3-none-any.whl", hash = "sha256:6b8733129a6224a9a711e17c99b08462dbf7cc9670ba8f2e2ae9af860ceb1953"},
+    {file = "alembic-1.13.2.tar.gz", hash = "sha256:1ff0ae32975f4fd96028c39ed9bb3c867fe3af956bd7bb37343b54c9fe7445ef"},
+]
+
+[package.dependencies]
+Mako = "*"
+SQLAlchemy = ">=1.3.0"
+typing-extensions = ">=4"
+
+[package.extras]
+tz = ["backports.zoneinfo"]
+
 [[package]]
 name = "appdirs"
 version = "1.4.4"
@@ -276,17 +295,6 @@ webencodings = "*"
 [package.extras]
 css = ["tinycss2 (>=1.1.0,<1.2)"]
 
-[[package]]
-name = "blinker"
-version = "1.6.2"
-description = "Fast, simple object-to-object and broadcast signaling"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "blinker-1.6.2-py3-none-any.whl", hash = "sha256:c3d739772abb7bc2860abf5f2ec284223d9ad5c76da018234f6f50d6f31ab1f0"},
-    {file = "blinker-1.6.2.tar.gz", hash = "sha256:4afd3de66ef3a9f8067559fb7a1cbe555c17dcbe15971b05d1b625c3e7abe213"},
-]
-
 [[package]]
 name = "brotli"
 version = "1.0.9"
@@ -658,6 +666,23 @@ files = [
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
 
+[[package]]
+name = "colorlog"
+version = "6.8.2"
+description = "Add colours to the output of Python's logging module."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "colorlog-6.8.2-py3-none-any.whl", hash = "sha256:4dcbb62368e2800cb3c5abd348da7e53f6c362dda502ec27c560b2e58a66bd33"},
+    {file = "colorlog-6.8.2.tar.gz", hash = "sha256:3e3e079a41feb5a1b64f978b5ea4f46040a94f11f0e8bbb8261e3dbbeca64d44"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+
+[package.extras]
+development = ["black", "flake8", "mypy", "pytest", "types-colorama"]
+
 [[package]]
 name = "comm"
 version = "0.1.3"
@@ -751,6 +776,24 @@ mypy = ["contourpy[bokeh]", "docutils-stubs", "mypy (==0.991)", "types-Pillow"]
 test = ["Pillow", "matplotlib", "pytest"]
 test-no-images = ["pytest"]
 
+[[package]]
+name = "coreforecast"
+version = "0.0.12"
+description = "Fast implementations of common forecasting routines"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "coreforecast-0.0.12-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:51a13bb737e06276b79a6e70016b9361b69859cc7020ea779116ba6bcd72c2d5"},
+    {file = "coreforecast-0.0.12-py3-none-macosx_11_0_arm64.whl", hash = "sha256:761a73c0c15df7008852f55cae6f0001e069447ee28b7d1f1fe14825497a91d1"},
+    {file = "coreforecast-0.0.12-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25eb7670c4b29324c8ddc52454038ade843ced8882009b11085ed5dca7bbf0f9"},
+    {file = "coreforecast-0.0.12-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:befcf2991a0f605c110462ea38ec8d115799f44d26e733cd2baa590f0aaea889"},
+    {file = "coreforecast-0.0.12-py3-none-win_amd64.whl", hash = "sha256:1e50d085cd40d4aeec957edbc50b230ae6df5985b946c9f2ad02f6cc2cb79a9c"},
+    {file = "coreforecast-0.0.12.tar.gz", hash = "sha256:52af687933d0d6a61a8fabdc656b3fc2b62ac55cd44739e5ebb456afdd759bd3"},
+]
+
+[package.dependencies]
+numpy = ">=1.20.0"
+
 [[package]]
 name = "cssselect2"
 version = "0.7.0"
@@ -866,63 +909,28 @@ xarray = ">=0.17.0"
 xgboost = ">=1.6.0"
 
 [[package]]
-name = "dash"
-version = "2.9.3"
-description = "A Python framework for building reactive web-apps. Developed by Plotly."
+name = "datasetsforecast"
+version = "0.0.8"
+description = "Datasets for Time series forecasting"
 optional = false
-python-versions = ">=3.6"
+python-versions = ">=3.7"
 files = [
-    {file = "dash-2.9.3-py3-none-any.whl", hash = "sha256:a749ae1ea9de3fe7b785353a818ec9b629d39c6b7e02462954203bd1e296fd0e"},
-    {file = "dash-2.9.3.tar.gz", hash = "sha256:47392f8d6455dc989a697407eb5941f3bad80604df985ab1ac9d4244568ffb34"},
+    {file = "datasetsforecast-0.0.8-py3-none-any.whl", hash = "sha256:54bf52903227ea93867fbfe06aaea57e24d5978338718a4f6a95c3be6b0170fd"},
+    {file = "datasetsforecast-0.0.8.tar.gz", hash = "sha256:41b8970d1443403e68d08b58d043c1308705bd115e3799a7df085cc6c5ec2814"},
 ]
 
 [package.dependencies]
-dash-core-components = "2.0.0"
-dash-html-components = "2.0.0"
-dash-table = "5.0.0"
-Flask = ">=1.0.4"
-plotly = ">=5.0.0"
+aiohttp = "*"
+fugue = ">=0.8.1"
+numba = "*"
+numpy = "*"
+pandas = "*"
+requests = "*"
+tqdm = "*"
+xlrd = ">=1.0.0"
 
 [package.extras]
-celery = ["celery[redis] (>=5.1.2)", "importlib-metadata (<5)", "redis (>=3.5.3)"]
-ci = ["black (==21.6b0)", "black (==22.3.0)", "dash-dangerously-set-inner-html", "dash-flow-example (==0.0.5)", "flake8 (==3.9.2)", "flaky (==3.7.0)", "flask-talisman (==1.0.0)", "isort (==4.3.21)", "mimesis", "mock (==4.0.3)", "numpy", "openpyxl", "orjson (==3.5.4)", "orjson (==3.6.7)", "pandas (==1.1.5)", "pandas (>=1.4.0)", "preconditions", "pyarrow", "pyarrow (<3)", "pylint (==2.13.5)", "pytest-mock", "pytest-rerunfailures", "pytest-sugar (==0.9.6)", "xlrd (<2)", "xlrd (>=2.0.1)"]
-compress = ["flask-compress"]
-dev = ["PyYAML (>=5.4.1)", "coloredlogs (>=15.0.1)", "fire (>=0.4.0)"]
-diskcache = ["diskcache (>=5.2.1)", "multiprocess (>=0.70.12)", "psutil (>=5.8.0)"]
-testing = ["beautifulsoup4 (>=4.8.2)", "cryptography (<3.4)", "dash-testing-stub (>=0.0.2)", "lxml (>=4.6.2)", "multiprocess (>=0.70.12)", "percy (>=2.0.2)", "psutil (>=5.8.0)", "pytest (>=6.0.2)", "requests[security] (>=2.21.0)", "selenium (>=3.141.0,<=4.2.0)", "waitress (>=1.4.4)"]
-
-[[package]]
-name = "dash-core-components"
-version = "2.0.0"
-description = "Core component suite for Dash"
-optional = false
-python-versions = "*"
-files = [
-    {file = "dash_core_components-2.0.0-py3-none-any.whl", hash = "sha256:52b8e8cce13b18d0802ee3acbc5e888cb1248a04968f962d63d070400af2e346"},
-    {file = "dash_core_components-2.0.0.tar.gz", hash = "sha256:c6733874af975e552f95a1398a16c2ee7df14ce43fa60bb3718a3c6e0b63ffee"},
-]
-
-[[package]]
-name = "dash-html-components"
-version = "2.0.0"
-description = "Vanilla HTML components for Dash"
-optional = false
-python-versions = "*"
-files = [
-    {file = "dash_html_components-2.0.0-py3-none-any.whl", hash = "sha256:b42cc903713c9706af03b3f2548bda4be7307a7cf89b7d6eae3da872717d1b63"},
-    {file = "dash_html_components-2.0.0.tar.gz", hash = "sha256:8703a601080f02619a6390998e0b3da4a5daabe97a1fd7a9cebc09d015f26e50"},
-]
-
-[[package]]
-name = "dash-table"
-version = "5.0.0"
-description = "Dash table"
-optional = false
-python-versions = "*"
-files = [
-    {file = "dash_table-5.0.0-py3-none-any.whl", hash = "sha256:19036fa352bb1c11baf38068ec62d172f0515f73ca3276c79dee49b95ddc16c9"},
-    {file = "dash_table-5.0.0.tar.gz", hash = "sha256:18624d693d4c8ef2ddec99a6f167593437a7ea0bf153aa20f318c170c5bc7308"},
-]
+dev = ["fugue[dask,ray] (>=0.8.1)"]
 
 [[package]]
 name = "debugpy"
@@ -1045,28 +1053,6 @@ files = [
 docs = ["furo (>=2023.3.27)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.2.3)", "diff-cover (>=7.5)", "pytest (>=7.3.1)", "pytest-cov (>=4)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"]
 
-[[package]]
-name = "flask"
-version = "2.3.2"
-description = "A simple framework for building complex web applications."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "Flask-2.3.2-py3-none-any.whl", hash = "sha256:77fd4e1249d8c9923de34907236b747ced06e5467ecac1a7bb7115ae0e9670b0"},
-    {file = "Flask-2.3.2.tar.gz", hash = "sha256:8c2f9abd47a9e8df7f0c3f091ce9497d011dc3b31effcf4c85a6e2b50f4114ef"},
-]
-
-[package.dependencies]
-blinker = ">=1.6.2"
-click = ">=8.1.3"
-itsdangerous = ">=2.1.2"
-Jinja2 = ">=3.1.2"
-Werkzeug = ">=2.3.3"
-
-[package.extras]
-async = ["asgiref (>=3.2)"]
-dotenv = ["python-dotenv"]
-
 [[package]]
 name = "fonttools"
 version = "4.39.4"
@@ -1355,6 +1341,77 @@ requests-oauthlib = ">=0.7.0"
 [package.extras]
 tool = ["click (>=6.0.0)"]
 
+[[package]]
+name = "greenlet"
+version = "3.0.3"
+description = "Lightweight in-process concurrent programming"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "greenlet-3.0.3-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:9da2bd29ed9e4f15955dd1595ad7bc9320308a3b766ef7f837e23ad4b4aac31a"},
+    {file = "greenlet-3.0.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d353cadd6083fdb056bb46ed07e4340b0869c305c8ca54ef9da3421acbdf6881"},
+    {file = "greenlet-3.0.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dca1e2f3ca00b84a396bc1bce13dd21f680f035314d2379c4160c98153b2059b"},
+    {file = "greenlet-3.0.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3ed7fb269f15dc662787f4119ec300ad0702fa1b19d2135a37c2c4de6fadfd4a"},
+    {file = "greenlet-3.0.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd4f49ae60e10adbc94b45c0b5e6a179acc1736cf7a90160b404076ee283cf83"},
+    {file = "greenlet-3.0.3-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:73a411ef564e0e097dbe7e866bb2dda0f027e072b04da387282b02c308807405"},
+    {file = "greenlet-3.0.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:7f362975f2d179f9e26928c5b517524e89dd48530a0202570d55ad6ca5d8a56f"},
+    {file = "greenlet-3.0.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:649dde7de1a5eceb258f9cb00bdf50e978c9db1b996964cd80703614c86495eb"},
+    {file = "greenlet-3.0.3-cp310-cp310-win_amd64.whl", hash = "sha256:68834da854554926fbedd38c76e60c4a2e3198c6fbed520b106a8986445caaf9"},
+    {file = "greenlet-3.0.3-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:b1b5667cced97081bf57b8fa1d6bfca67814b0afd38208d52538316e9422fc61"},
+    {file = "greenlet-3.0.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:52f59dd9c96ad2fc0d5724107444f76eb20aaccb675bf825df6435acb7703559"},
+    {file = "greenlet-3.0.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:afaff6cf5200befd5cec055b07d1c0a5a06c040fe5ad148abcd11ba6ab9b114e"},
+    {file = "greenlet-3.0.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fe754d231288e1e64323cfad462fcee8f0288654c10bdf4f603a39ed923bef33"},
+    {file = "greenlet-3.0.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2797aa5aedac23af156bbb5a6aa2cd3427ada2972c828244eb7d1b9255846379"},
+    {file = "greenlet-3.0.3-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b7f009caad047246ed379e1c4dbcb8b020f0a390667ea74d2387be2998f58a22"},
+    {file = "greenlet-3.0.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c5e1536de2aad7bf62e27baf79225d0d64360d4168cf2e6becb91baf1ed074f3"},
+    {file = "greenlet-3.0.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:894393ce10ceac937e56ec00bb71c4c2f8209ad516e96033e4b3b1de270e200d"},
+    {file = "greenlet-3.0.3-cp311-cp311-win_amd64.whl", hash = "sha256:1ea188d4f49089fc6fb283845ab18a2518d279c7cd9da1065d7a84e991748728"},
+    {file = "greenlet-3.0.3-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:70fb482fdf2c707765ab5f0b6655e9cfcf3780d8d87355a063547b41177599be"},
+    {file = "greenlet-3.0.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d4d1ac74f5c0c0524e4a24335350edad7e5f03b9532da7ea4d3c54d527784f2e"},
+    {file = "greenlet-3.0.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:149e94a2dd82d19838fe4b2259f1b6b9957d5ba1b25640d2380bea9c5df37676"},
+    {file = "greenlet-3.0.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:15d79dd26056573940fcb8c7413d84118086f2ec1a8acdfa854631084393efcc"},
+    {file = "greenlet-3.0.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881b7db1ebff4ba09aaaeae6aa491daeb226c8150fc20e836ad00041bcb11230"},
+    {file = "greenlet-3.0.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fcd2469d6a2cf298f198f0487e0a5b1a47a42ca0fa4dfd1b6862c999f018ebbf"},
+    {file = "greenlet-3.0.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:1f672519db1796ca0d8753f9e78ec02355e862d0998193038c7073045899f305"},
+    {file = "greenlet-3.0.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2516a9957eed41dd8f1ec0c604f1cdc86758b587d964668b5b196a9db5bfcde6"},
+    {file = "greenlet-3.0.3-cp312-cp312-win_amd64.whl", hash = "sha256:bba5387a6975598857d86de9eac14210a49d554a77eb8261cc68b7d082f78ce2"},
+    {file = "greenlet-3.0.3-cp37-cp37m-macosx_11_0_universal2.whl", hash = "sha256:5b51e85cb5ceda94e79d019ed36b35386e8c37d22f07d6a751cb659b180d5274"},
+    {file = "greenlet-3.0.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:daf3cb43b7cf2ba96d614252ce1684c1bccee6b2183a01328c98d36fcd7d5cb0"},
+    {file = "greenlet-3.0.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:99bf650dc5d69546e076f413a87481ee1d2d09aaaaaca058c9251b6d8c14783f"},
+    {file = "greenlet-3.0.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2dd6e660effd852586b6a8478a1d244b8dc90ab5b1321751d2ea15deb49ed414"},
+    {file = "greenlet-3.0.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3391d1e16e2a5a1507d83e4a8b100f4ee626e8eca43cf2cadb543de69827c4c"},
+    {file = "greenlet-3.0.3-cp37-cp37m-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e1f145462f1fa6e4a4ae3c0f782e580ce44d57c8f2c7aae1b6fa88c0b2efdb41"},
+    {file = "greenlet-3.0.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:1a7191e42732df52cb5f39d3527217e7ab73cae2cb3694d241e18f53d84ea9a7"},
+    {file = "greenlet-3.0.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:0448abc479fab28b00cb472d278828b3ccca164531daab4e970a0458786055d6"},
+    {file = "greenlet-3.0.3-cp37-cp37m-win32.whl", hash = "sha256:b542be2440edc2d48547b5923c408cbe0fc94afb9f18741faa6ae970dbcb9b6d"},
+    {file = "greenlet-3.0.3-cp37-cp37m-win_amd64.whl", hash = "sha256:01bc7ea167cf943b4c802068e178bbf70ae2e8c080467070d01bfa02f337ee67"},
+    {file = "greenlet-3.0.3-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:1996cb9306c8595335bb157d133daf5cf9f693ef413e7673cb07e3e5871379ca"},
+    {file = "greenlet-3.0.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ddc0f794e6ad661e321caa8d2f0a55ce01213c74722587256fb6566049a8b04"},
+    {file = "greenlet-3.0.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c9db1c18f0eaad2f804728c67d6c610778456e3e1cc4ab4bbd5eeb8e6053c6fc"},
+    {file = "greenlet-3.0.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7170375bcc99f1a2fbd9c306f5be8764eaf3ac6b5cb968862cad4c7057756506"},
+    {file = "greenlet-3.0.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b66c9c1e7ccabad3a7d037b2bcb740122a7b17a53734b7d72a344ce39882a1b"},
+    {file = "greenlet-3.0.3-cp38-cp38-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:098d86f528c855ead3479afe84b49242e174ed262456c342d70fc7f972bc13c4"},
+    {file = "greenlet-3.0.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:81bb9c6d52e8321f09c3d165b2a78c680506d9af285bfccbad9fb7ad5a5da3e5"},
+    {file = "greenlet-3.0.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fd096eb7ffef17c456cfa587523c5f92321ae02427ff955bebe9e3c63bc9f0da"},
+    {file = "greenlet-3.0.3-cp38-cp38-win32.whl", hash = "sha256:d46677c85c5ba00a9cb6f7a00b2bfa6f812192d2c9f7d9c4f6a55b60216712f3"},
+    {file = "greenlet-3.0.3-cp38-cp38-win_amd64.whl", hash = "sha256:419b386f84949bf0e7c73e6032e3457b82a787c1ab4a0e43732898a761cc9dbf"},
+    {file = "greenlet-3.0.3-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:da70d4d51c8b306bb7a031d5cff6cc25ad253affe89b70352af5f1cb68e74b53"},
+    {file = "greenlet-3.0.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:086152f8fbc5955df88382e8a75984e2bb1c892ad2e3c80a2508954e52295257"},
+    {file = "greenlet-3.0.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d73a9fe764d77f87f8ec26a0c85144d6a951a6c438dfe50487df5595c6373eac"},
+    {file = "greenlet-3.0.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b7dcbe92cc99f08c8dd11f930de4d99ef756c3591a5377d1d9cd7dd5e896da71"},
+    {file = "greenlet-3.0.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1551a8195c0d4a68fac7a4325efac0d541b48def35feb49d803674ac32582f61"},
+    {file = "greenlet-3.0.3-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:64d7675ad83578e3fc149b617a444fab8efdafc9385471f868eb5ff83e446b8b"},
+    {file = "greenlet-3.0.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:b37eef18ea55f2ffd8f00ff8fe7c8d3818abd3e25fb73fae2ca3b672e333a7a6"},
+    {file = "greenlet-3.0.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:77457465d89b8263bca14759d7c1684df840b6811b2499838cc5b040a8b5b113"},
+    {file = "greenlet-3.0.3-cp39-cp39-win32.whl", hash = "sha256:57e8974f23e47dac22b83436bdcf23080ade568ce77df33159e019d161ce1d1e"},
+    {file = "greenlet-3.0.3-cp39-cp39-win_amd64.whl", hash = "sha256:c5ee858cfe08f34712f548c3c363e807e7186f03ad7a5039ebadb29e8c6be067"},
+    {file = "greenlet-3.0.3.tar.gz", hash = "sha256:43374442353259554ce33599da8b692d5aa96f8976d567d4badf263371fbe491"},
+]
+
+[package.extras]
+docs = ["Sphinx", "furo"]
+test = ["objgraph", "psutil"]
+
 [[package]]
 name = "grpcio"
 version = "1.59.3"
@@ -1457,6 +1514,40 @@ chardet = ["chardet (>=2.2)"]
 genshi = ["genshi"]
 lxml = ["lxml"]
 
+[[package]]
+name = "huggingface-hub"
+version = "0.24.6"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "huggingface_hub-0.24.6-py3-none-any.whl", hash = "sha256:a990f3232aa985fe749bc9474060cbad75e8b2f115f6665a9fda5b9c97818970"},
+    {file = "huggingface_hub-0.24.6.tar.gz", hash = "sha256:cc2579e761d070713eaa9c323e3debe39d5b464ae3a7261c39a9195b27bb8000"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = ">=2023.5.0"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
+hf-transfer = ["hf-transfer (>=0.1.4)"]
+inference = ["aiohttp", "minijinja (>=1.0)"]
+quality = ["mypy (==1.5.1)", "ruff (>=0.5.0)"]
+tensorflow = ["graphviz", "pydot", "tensorflow"]
+tensorflow-testing = ["keras (<3.0)", "tensorflow"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
+torch = ["safetensors[torch]", "torch"]
+typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
+
 [[package]]
 name = "idna"
 version = "3.4"
@@ -1560,17 +1651,6 @@ widgetsnbextension = ">=4.0.9,<4.1.0"
 [package.extras]
 test = ["ipykernel", "jsonschema", "pytest (>=3.6.0)", "pytest-cov", "pytz"]
 
-[[package]]
-name = "itsdangerous"
-version = "2.1.2"
-description = "Safely pass data to untrusted environments and back."
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "itsdangerous-2.1.2-py3-none-any.whl", hash = "sha256:2c2349112351b88699d8d4b6b075022c0808887cb7ad10069318a8b0bc88db44"},
-    {file = "itsdangerous-2.1.2.tar.gz", hash = "sha256:5dbbc68b317e5e42f327f9021763545dc3fc3bfe22e6deb96aaf1fc38874156a"},
-]
-
 [[package]]
 name = "jedi"
 version = "0.18.2"
@@ -1970,6 +2050,25 @@ win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""}
 [package.extras]
 dev = ["Sphinx (==7.2.5)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptiongroup (==1.1.3)", "freezegun (==1.1.0)", "freezegun (==1.2.2)", "mypy (==v0.910)", "mypy (==v0.971)", "mypy (==v1.4.1)", "mypy (==v1.5.1)", "pre-commit (==3.4.0)", "pytest (==6.1.2)", "pytest (==7.4.0)", "pytest-cov (==2.12.1)", "pytest-cov (==4.1.0)", "pytest-mypy-plugins (==1.9.3)", "pytest-mypy-plugins (==3.0.0)", "sphinx-autobuild (==2021.3.14)", "sphinx-rtd-theme (==1.3.0)", "tox (==3.27.1)", "tox (==4.11.0)"]
 
+[[package]]
+name = "mako"
+version = "1.3.5"
+description = "A super-fast templating language that borrows the best ideas from the existing templating languages."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "Mako-1.3.5-py3-none-any.whl", hash = "sha256:260f1dbc3a519453a9c856dedfe4beb4e50bd5a26d96386cb6c80856556bb91a"},
+    {file = "Mako-1.3.5.tar.gz", hash = "sha256:48dbc20568c1d276a2698b36d968fa76161bf127194907ea6fc594fa81f943bc"},
+]
+
+[package.dependencies]
+MarkupSafe = ">=0.9.2"
+
+[package.extras]
+babel = ["Babel"]
+lingua = ["lingua"]
+testing = ["pytest"]
+
 [[package]]
 name = "markdown"
 version = "3.3.7"
@@ -2401,6 +2500,40 @@ crystal = ["mkdocstrings-crystal (>=0.3.4)"]
 python = ["mkdocstrings-python (>=0.5.2)"]
 python-legacy = ["mkdocstrings-python-legacy (>=0.2.1)"]
 
+[[package]]
+name = "mlforecast"
+version = "0.13.4"
+description = "Scalable machine learning based time series forecasting"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "mlforecast-0.13.4-py3-none-any.whl", hash = "sha256:a33be2671e3914f2271deb1a59ab8f50a8c02c617726fdc3232c4f38fdb4e992"},
+    {file = "mlforecast-0.13.4.tar.gz", hash = "sha256:ca55bd7ed1a167f7c6d23554816aa539e2f678a4758d11be7fad7a288f815ee6"},
+]
+
+[package.dependencies]
+cloudpickle = "*"
+coreforecast = ">=0.0.11"
+fsspec = "*"
+numba = "*"
+optuna = "*"
+packaging = "*"
+pandas = "*"
+scikit-learn = "*"
+utilsforecast = ">=0.1.9"
+window-ops = "*"
+
+[package.extras]
+all = ["black (>=24)", "dask[complete]", "datasetsforecast", "fsspec[adl]", "fsspec[gcs]", "fsspec[s3]", "fugue", "fugue[ray]", "gitpython", "holidays (<0.21)", "lightgbm", "lightgbm-ray", "matplotlib", "mlflow (>=2.10.0)", "mypy", "nbdev (<2.3.26)", "numpy (<2)", "pandas (<2.2)", "polars[numpy]", "pre-commit", "pyarrow", "pyspark (>=3.3)", "ray (<2.8)", "ruff", "setuptools (<70)", "shap", "statsmodels", "xgboost", "xgboost (<2)", "xgboost-ray"]
+aws = ["fsspec[s3]"]
+azure = ["fsspec[adl]"]
+dask = ["dask[complete]", "fugue", "lightgbm", "xgboost"]
+dev = ["black (>=24)", "datasetsforecast", "gitpython", "holidays (<0.21)", "lightgbm", "matplotlib", "mlflow (>=2.10.0)", "mypy", "nbdev (<2.3.26)", "polars[numpy]", "pre-commit", "pyarrow", "ruff", "shap", "statsmodels", "xgboost"]
+gcp = ["fsspec[gcs]"]
+polars = ["polars[numpy]"]
+ray = ["fugue[ray]", "lightgbm-ray", "numpy (<2)", "pandas (<2.2)", "ray (<2.8)", "setuptools (<70)", "xgboost (<2)", "xgboost-ray"]
+spark = ["fugue", "lightgbm", "pyspark (>=3.3)", "xgboost"]
+
 [[package]]
 name = "mpmath"
 version = "1.3.0"
@@ -2418,6 +2551,71 @@ docs = ["sphinx"]
 gmpy = ["gmpy2 (>=2.1.0a4)"]
 tests = ["pytest (>=4.6)"]
 
+[[package]]
+name = "msgpack"
+version = "1.0.8"
+description = "MessagePack serializer"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "msgpack-1.0.8-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:505fe3d03856ac7d215dbe005414bc28505d26f0c128906037e66d98c4e95868"},
+    {file = "msgpack-1.0.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e6b7842518a63a9f17107eb176320960ec095a8ee3b4420b5f688e24bf50c53c"},
+    {file = "msgpack-1.0.8-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:376081f471a2ef24828b83a641a02c575d6103a3ad7fd7dade5486cad10ea659"},
+    {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e390971d082dba073c05dbd56322427d3280b7cc8b53484c9377adfbae67dc2"},
+    {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00e073efcba9ea99db5acef3959efa45b52bc67b61b00823d2a1a6944bf45982"},
+    {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82d92c773fbc6942a7a8b520d22c11cfc8fd83bba86116bfcf962c2f5c2ecdaa"},
+    {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9ee32dcb8e531adae1f1ca568822e9b3a738369b3b686d1477cbc643c4a9c128"},
+    {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e3aa7e51d738e0ec0afbed661261513b38b3014754c9459508399baf14ae0c9d"},
+    {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:69284049d07fce531c17404fcba2bb1df472bc2dcdac642ae71a2d079d950653"},
+    {file = "msgpack-1.0.8-cp310-cp310-win32.whl", hash = "sha256:13577ec9e247f8741c84d06b9ece5f654920d8365a4b636ce0e44f15e07ec693"},
+    {file = "msgpack-1.0.8-cp310-cp310-win_amd64.whl", hash = "sha256:e532dbd6ddfe13946de050d7474e3f5fb6ec774fbb1a188aaf469b08cf04189a"},
+    {file = "msgpack-1.0.8-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9517004e21664f2b5a5fd6333b0731b9cf0817403a941b393d89a2f1dc2bd836"},
+    {file = "msgpack-1.0.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d16a786905034e7e34098634b184a7d81f91d4c3d246edc6bd7aefb2fd8ea6ad"},
+    {file = "msgpack-1.0.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e2872993e209f7ed04d963e4b4fbae72d034844ec66bc4ca403329db2074377b"},
+    {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c330eace3dd100bdb54b5653b966de7f51c26ec4a7d4e87132d9b4f738220ba"},
+    {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83b5c044f3eff2a6534768ccfd50425939e7a8b5cf9a7261c385de1e20dcfc85"},
+    {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1876b0b653a808fcd50123b953af170c535027bf1d053b59790eebb0aeb38950"},
+    {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:dfe1f0f0ed5785c187144c46a292b8c34c1295c01da12e10ccddfc16def4448a"},
+    {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:3528807cbbb7f315bb81959d5961855e7ba52aa60a3097151cb21956fbc7502b"},
+    {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e2f879ab92ce502a1e65fce390eab619774dda6a6ff719718069ac94084098ce"},
+    {file = "msgpack-1.0.8-cp311-cp311-win32.whl", hash = "sha256:26ee97a8261e6e35885c2ecd2fd4a6d38252246f94a2aec23665a4e66d066305"},
+    {file = "msgpack-1.0.8-cp311-cp311-win_amd64.whl", hash = "sha256:eadb9f826c138e6cf3c49d6f8de88225a3c0ab181a9b4ba792e006e5292d150e"},
+    {file = "msgpack-1.0.8-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:114be227f5213ef8b215c22dde19532f5da9652e56e8ce969bf0a26d7c419fee"},
+    {file = "msgpack-1.0.8-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d661dc4785affa9d0edfdd1e59ec056a58b3dbb9f196fa43587f3ddac654ac7b"},
+    {file = "msgpack-1.0.8-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d56fd9f1f1cdc8227d7b7918f55091349741904d9520c65f0139a9755952c9e8"},
+    {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0726c282d188e204281ebd8de31724b7d749adebc086873a59efb8cf7ae27df3"},
+    {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8db8e423192303ed77cff4dce3a4b88dbfaf43979d280181558af5e2c3c71afc"},
+    {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:99881222f4a8c2f641f25703963a5cefb076adffd959e0558dc9f803a52d6a58"},
+    {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b5505774ea2a73a86ea176e8a9a4a7c8bf5d521050f0f6f8426afe798689243f"},
+    {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:ef254a06bcea461e65ff0373d8a0dd1ed3aa004af48839f002a0c994a6f72d04"},
+    {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e1dd7839443592d00e96db831eddb4111a2a81a46b028f0facd60a09ebbdd543"},
+    {file = "msgpack-1.0.8-cp312-cp312-win32.whl", hash = "sha256:64d0fcd436c5683fdd7c907eeae5e2cbb5eb872fafbc03a43609d7941840995c"},
+    {file = "msgpack-1.0.8-cp312-cp312-win_amd64.whl", hash = "sha256:74398a4cf19de42e1498368c36eed45d9528f5fd0155241e82c4082b7e16cffd"},
+    {file = "msgpack-1.0.8-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:0ceea77719d45c839fd73abcb190b8390412a890df2f83fb8cf49b2a4b5c2f40"},
+    {file = "msgpack-1.0.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1ab0bbcd4d1f7b6991ee7c753655b481c50084294218de69365f8f1970d4c151"},
+    {file = "msgpack-1.0.8-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1cce488457370ffd1f953846f82323cb6b2ad2190987cd4d70b2713e17268d24"},
+    {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3923a1778f7e5ef31865893fdca12a8d7dc03a44b33e2a5f3295416314c09f5d"},
+    {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a22e47578b30a3e199ab067a4d43d790249b3c0587d9a771921f86250c8435db"},
+    {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd739c9251d01e0279ce729e37b39d49a08c0420d3fee7f2a4968c0576678f77"},
+    {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d3420522057ebab1728b21ad473aa950026d07cb09da41103f8e597dfbfaeb13"},
+    {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5845fdf5e5d5b78a49b826fcdc0eb2e2aa7191980e3d2cfd2a30303a74f212e2"},
+    {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6a0e76621f6e1f908ae52860bdcb58e1ca85231a9b0545e64509c931dd34275a"},
+    {file = "msgpack-1.0.8-cp38-cp38-win32.whl", hash = "sha256:374a8e88ddab84b9ada695d255679fb99c53513c0a51778796fcf0944d6c789c"},
+    {file = "msgpack-1.0.8-cp38-cp38-win_amd64.whl", hash = "sha256:f3709997b228685fe53e8c433e2df9f0cdb5f4542bd5114ed17ac3c0129b0480"},
+    {file = "msgpack-1.0.8-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f51bab98d52739c50c56658cc303f190785f9a2cd97b823357e7aeae54c8f68a"},
+    {file = "msgpack-1.0.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:73ee792784d48aa338bba28063e19a27e8d989344f34aad14ea6e1b9bd83f596"},
+    {file = "msgpack-1.0.8-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f9904e24646570539a8950400602d66d2b2c492b9010ea7e965025cb71d0c86d"},
+    {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e75753aeda0ddc4c28dce4c32ba2f6ec30b1b02f6c0b14e547841ba5b24f753f"},
+    {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5dbf059fb4b7c240c873c1245ee112505be27497e90f7c6591261c7d3c3a8228"},
+    {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4916727e31c28be8beaf11cf117d6f6f188dcc36daae4e851fee88646f5b6b18"},
+    {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7938111ed1358f536daf311be244f34df7bf3cdedb3ed883787aca97778b28d8"},
+    {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:493c5c5e44b06d6c9268ce21b302c9ca055c1fd3484c25ba41d34476c76ee746"},
+    {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5fbb160554e319f7b22ecf530a80a3ff496d38e8e07ae763b9e82fadfe96f273"},
+    {file = "msgpack-1.0.8-cp39-cp39-win32.whl", hash = "sha256:f9af38a89b6a5c04b7d18c492c8ccf2aee7048aff1ce8437c4683bb5a1df893d"},
+    {file = "msgpack-1.0.8-cp39-cp39-win_amd64.whl", hash = "sha256:ed59dd52075f8fc91da6053b12e8c89e37aa043f8986efd89e61fae69dc1b011"},
+    {file = "msgpack-1.0.8.tar.gz", hash = "sha256:95c02b0e27e706e48d0e5426d1710ca78e0f0628d6e89d5b5a5b91a5f12274f3"},
+]
+
 [[package]]
 name = "multidict"
 version = "6.0.5"
@@ -2626,6 +2824,33 @@ doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-
 extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
 test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
 
+[[package]]
+name = "neuralforecast"
+version = "1.7.4"
+description = "Time series forecasting suite using deep learning models"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "neuralforecast-1.7.4-py3-none-any.whl", hash = "sha256:106ad71cb00b6462e28350391d2809e2cd1089f7d8b1cfab766e8ce2551894b7"},
+    {file = "neuralforecast-1.7.4.tar.gz", hash = "sha256:02b6f7bfc1c472ca603deeb65ce76063bcfc4e195eb6ff8b1c6b4076d1f903e5"},
+]
+
+[package.dependencies]
+coreforecast = ">=0.0.6"
+fsspec = "*"
+numpy = ">=1.21.6"
+optuna = "*"
+pandas = ">=1.3.5"
+pytorch-lightning = ">=2.0.0"
+ray = {version = ">=2.2.0", extras = ["tune"]}
+torch = ">=2.0.0"
+utilsforecast = ">=0.0.25"
+
+[package.extras]
+aws = ["fsspec[s3]"]
+dev = ["black", "gitpython", "hyperopt", "matplotlib", "mypy", "nbdev (==2.3.25)", "polars", "pre-commit", "pyarrow", "ruff", "s3fs", "transformers"]
+spark = ["fugue", "pyspark (>=3.5)"]
+
 [[package]]
 name = "nfoursid"
 version = "1.0.1"
@@ -2733,60 +2958,32 @@ signals = ["blinker (>=1.4.0)"]
 signedtoken = ["cryptography (>=3.0.0)", "pyjwt (>=2.0.0,<3)"]
 
 [[package]]
-name = "orjson"
-version = "3.8.12"
-description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
+name = "optuna"
+version = "4.0.0"
+description = "A hyperparameter optimization framework"
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "orjson-3.8.12-cp310-cp310-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:c84046e890e13a119404a83f2e09e622509ed4692846ff94c4ca03654fbc7fb5"},
-    {file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29706dd8189835bcf1781faed286e99ae54fd6165437d364dfdbf0276bf39b19"},
-    {file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f4e22b0aa70c963ac01fcd620de15be21a5027711b0e5d4b96debcdeea43e3ae"},
-    {file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6d1acf52d3a4b9384af09a5c2658c3a7a472a4d62a0ad1fe2c8fab8ef460c9b4"},
-    {file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a72b50719bdd6bb0acfca3d4d1c841aa4b191f3ff37268e7aba04e5d6be44ccd"},
-    {file = "orjson-3.8.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83e8c740a718fa6d511a82e463adc7ab17631c6eea81a716b723e127a9c51d57"},
-    {file = "orjson-3.8.12-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:ebb03e4c7648f7bb299872002a6120082da018f41ba7a9ebf4ceae8d765443d2"},
-    {file = "orjson-3.8.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:44f7bb4c995652106276442de1147c9993716d1e2d79b7fd435afa154ff236b9"},
-    {file = "orjson-3.8.12-cp310-none-win_amd64.whl", hash = "sha256:06e528f9a84fbb4000fd0eee573b5db543ee70ae586fdbc53e740b0ac981701c"},
-    {file = "orjson-3.8.12-cp311-cp311-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:9a6c1594d5a9ff56e5babc4a87ac372af38d37adef9e06744e9f158431e33f43"},
-    {file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6390ce0bce24c107fc275736aa8a4f768ef7eb5df935d7dca0cc99815eb5d99"},
-    {file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:efb3a10030462a22c731682434df5c137a67632a8339f821cd501920b169007e"},
-    {file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7e405d54c84c30d9b1c918c290bcf4ef484a45c69d5583a95db81ffffba40b44"},
-    {file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd6fbd1413559572e81b5ac64c45388147c3ba85cc3df2eaa11002945e0dbd1f"},
-    {file = "orjson-3.8.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f480ae7b84369b1860d8867f0baf8d885fede400fda390ce088bfa8edf97ffdc"},
-    {file = "orjson-3.8.12-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:355055e0977c43b0e5325b9312b7208c696fe20cd54eed1d6fc80b0a4d6721f5"},
-    {file = "orjson-3.8.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d937503e4dfba5edc8d5e0426d3cc97ed55716e93212b2e12a198664487b9965"},
-    {file = "orjson-3.8.12-cp311-none-win_amd64.whl", hash = "sha256:eb16e0195febd24b44f4db1ab3be85ecf6038f92fd511370cebc004b3d422294"},
-    {file = "orjson-3.8.12-cp37-cp37m-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:dc27a8ec13f28e92dc1ea89bf1232d77e7d3ebfd5c1ccf4f3729a70561cb63bd"},
-    {file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77710774faed337ac4ad919dadc5f3b655b0cd40518e5386e6f1f116de9c6c25"},
-    {file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7e549468867991f6f9cfbd9c5bbc977330173bd8f6ceb79973bbd4634e13e1b9"},
-    {file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:96fb1eb82b578eb6c0e53e3cf950839fe98ea210626f87c8204bd4fc2cc6ba02"},
-    {file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d153b228b6e24f8bccf732a51e01e8e938eef59efed9030c5c257778fbe0804"},
-    {file = "orjson-3.8.12-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:becbd5af6d035a7ec2ee3239d4700929d52d8517806b97dd04efcc37289403f7"},
-    {file = "orjson-3.8.12-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7d63f524048825e05950db3b6998c756d5377a5e8c469b2e3bdb9f3217523d74"},
-    {file = "orjson-3.8.12-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ec4f0130d9a27cb400423e09e0f9e46480e9e977f05fdcf663a7a2c68735513e"},
-    {file = "orjson-3.8.12-cp37-none-win_amd64.whl", hash = "sha256:6f1b01f641f5e87168b819ac1cbd81aa6278e7572c326f3d27e92dea442a2c0d"},
-    {file = "orjson-3.8.12-cp38-cp38-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:062e67108c218fdb9475edd5272b1629c05b56c66416fa915de5656adde30e73"},
-    {file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ba645c92801417933fa74448622ba614a275ea82df05e888095c7742d913bb4"},
-    {file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7d50d9b1ae409ea15534365fec0ce8a5a5f7dc94aa790aacfb8cfec87ab51aa4"},
-    {file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8f00038bf5d07439d13c0c2c5cd6ad48eb86df7dbd7a484013ce6a113c421b14"},
-    {file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:397670665f94cf5cff779054781d80395084ba97191d82f7b3a86f0a20e6102b"},
-    {file = "orjson-3.8.12-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f568205519bb0197ca91915c5da6058cfbb59993e557b02dfc3b2718b34770a"},
-    {file = "orjson-3.8.12-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:4fd240e736ce52cd757d74142d9933fd35a3184396be887c435f0574e0388654"},
-    {file = "orjson-3.8.12-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6cae2ff288a80e81ce30313e735c5436495ab58cf8d4fbe84900e616d0ee7a78"},
-    {file = "orjson-3.8.12-cp38-none-win_amd64.whl", hash = "sha256:710c40c214b753392e46f9275fd795e9630dd737a5ab4ac6e4ee1a02fe83cc0d"},
-    {file = "orjson-3.8.12-cp39-cp39-macosx_11_0_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:aff761de5ed5543a0a51e9f703668624749aa2239de5d7d37d9c9693daeaf5dc"},
-    {file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:135f29cf936283a0cd1b8bce86540ca181108f2a4d4483eedad6b8026865d2a9"},
-    {file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:62f999798f2fa55e567d483864ebfc30120fb055c2696a255979439323a5b15c"},
-    {file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3fa58ca064c640fa9d823f98fbbc8e71940ecb78cea3ac2507da1cbf49d60b51"},
-    {file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8682f752c19f6a7d9fc727fd98588b4c8b0dce791b5794bb814c7379ccd64a79"},
-    {file = "orjson-3.8.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de3d096dde3e46d01841abc1982b906694ab3c92f338d37a2e6184739dc8a958"},
-    {file = "orjson-3.8.12-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:834b50df79f1fe89bbaced3a1c1d8c8c92cc99e84cdcd374d8da4974b3560d2a"},
-    {file = "orjson-3.8.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:2ad149ed76dce2bbdfbadd61c35959305e77141badf364a158beb4ef3d88ec37"},
-    {file = "orjson-3.8.12-cp39-none-win_amd64.whl", hash = "sha256:82d65e478a21f98107b4eb8390104746bb3024c27084b57edab7d427385f1f70"},
-    {file = "orjson-3.8.12.tar.gz", hash = "sha256:9f0f042cf002a474a6aea006dd9f8d7a5497e35e5fb190ec78eb4d232ec19955"},
+    {file = "optuna-4.0.0-py3-none-any.whl", hash = "sha256:a825c32d13f6085bcb2229b2724a5078f2e0f61a7533e800e580ce41a8c6c10d"},
+    {file = "optuna-4.0.0.tar.gz", hash = "sha256:844949f09e2a7353ab414e9cfd783cf0a647a65fc32a7236212ed6a37fe08973"},
 ]
 
+[package.dependencies]
+alembic = ">=1.5.0"
+colorlog = "*"
+numpy = "*"
+packaging = ">=20.0"
+PyYAML = "*"
+sqlalchemy = ">=1.3.0"
+tqdm = "*"
+
+[package.extras]
+benchmark = ["asv (>=0.5.0)", "botorch", "cma", "virtualenv"]
+checking = ["black", "blackdoc", "flake8", "isort", "mypy", "mypy-boto3-s3", "types-PyYAML", "types-redis", "types-setuptools", "types-tqdm", "typing-extensions (>=3.10.0.0)"]
+document = ["ase", "cmaes (>=0.10.0)", "fvcore", "kaleido", "lightgbm", "matplotlib (!=3.6.0)", "pandas", "pillow", "plotly (>=4.9.0)", "scikit-learn", "sphinx", "sphinx-copybutton", "sphinx-gallery", "sphinx-rtd-theme (>=1.2.0)", "torch", "torchvision"]
+optional = ["boto3", "cmaes (>=0.10.0)", "google-cloud-storage", "matplotlib (!=3.6.0)", "pandas", "plotly (>=4.9.0)", "redis", "scikit-learn (>=0.24.2)", "scipy", "torch"]
+test = ["coverage", "fakeredis[lua]", "kaleido", "moto", "pytest", "scipy (>=1.9.2)", "torch"]
+
 [[package]]
 name = "packaging"
 version = "23.1"
@@ -3062,43 +3259,6 @@ files = [
 docs = ["furo (>=2023.3.27)", "proselint (>=0.13)", "sphinx (>=6.2.1)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"]
 test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.3.1)", "pytest-cov (>=4)", "pytest-mock (>=3.10)"]
 
-[[package]]
-name = "plotly"
-version = "5.14.1"
-description = "An open-source, interactive data visualization library for Python"
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "plotly-5.14.1-py2.py3-none-any.whl", hash = "sha256:a63f3ad9e4cc2e02902a738e5e3e7f3d1307f2732ac71a6c28f1238ed3052826"},
-    {file = "plotly-5.14.1.tar.gz", hash = "sha256:bcac86d7fcba3eff7260c1eddc36ca34dae2aded10a0709808446565e0e53b93"},
-]
-
-[package.dependencies]
-packaging = "*"
-tenacity = ">=6.2.0"
-
-[[package]]
-name = "plotly-resampler"
-version = "0.10.0"
-description = "Visualizing large time series with plotly"
-optional = false
-python-versions = "<4.0.0,>=3.7.1"
-files = [
-    {file = "plotly_resampler-0.10.0-py3-none-any.whl", hash = "sha256:4d695557fe8a718b4a3f45a5381fae6faca0e441d04b6d83d6b43ce998013355"},
-    {file = "plotly_resampler-0.10.0.tar.gz", hash = "sha256:e1063d6d00aa4aedeb8c2c204de8661751b2145fd06682cd8fead9983c9a8334"},
-]
-
-[package.dependencies]
-dash = ">=2.9.0"
-numpy = {version = ">=1.14", markers = "python_version < \"3.11\""}
-orjson = ">=3.8.0,<4.0.0"
-pandas = ">=1"
-plotly = ">=5.5.0,<6.0.0"
-tsdownsample = ">=0.1.3"
-
-[package.extras]
-inline-persistent = ["Flask-Cors (>=3.0.10,<4.0.0)", "jupyter-dash (>=0.4.2)", "kaleido (==0.2.1)"]
-
 [[package]]
 name = "pmdarima"
 version = "2.0.3"
@@ -3779,6 +3939,67 @@ files = [
 [package.dependencies]
 cffi = {version = "*", markers = "implementation_name == \"pypy\""}
 
+[[package]]
+name = "ray"
+version = "2.35.0"
+description = "Ray provides a simple, universal API for building distributed applications."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "ray-2.35.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:1e7e2d2e987be728a81821b6fd2bccb23e4d8a6cca8417db08b24f06a08d8476"},
+    {file = "ray-2.35.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8bd48be4c362004d31e5df072fd58b929efc67adfefc0adece41483b15f84539"},
+    {file = "ray-2.35.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:ef41e9254f3e18a90a8cf13fac9e35ac086eb778079ab6c76a37d3a6059186c5"},
+    {file = "ray-2.35.0-cp310-cp310-manylinux2014_x86_64.whl", hash = "sha256:1994aaf9996ffc45019856545e817d527ad572762f1af76ad669ae4e786fcfd6"},
+    {file = "ray-2.35.0-cp310-cp310-win_amd64.whl", hash = "sha256:d3b7a7d73f818e249064460ffa95402ebd852bf97d9ec6167b8b0d95be03da9f"},
+    {file = "ray-2.35.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:e29754fac4b69a9cb0d089841af59ec6fb10b5d4a248b7c579d319ca2ed1c96f"},
+    {file = "ray-2.35.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d7a606c8ca53c64fc496703e9fd15d1a1ffb50e6b457a33d3622be2f13fc30a5"},
+    {file = "ray-2.35.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:ac561e20a62ce941b74d02a0b92b7765c6ba87cc22e24f34f64ded2c454ba64e"},
+    {file = "ray-2.35.0-cp311-cp311-manylinux2014_x86_64.whl", hash = "sha256:587af570cbe5f6cedca854f15107740e63c67207bee900713cb2ee38f6ebf20f"},
+    {file = "ray-2.35.0-cp311-cp311-win_amd64.whl", hash = "sha256:8e406cce41679790146d4d2b1b0cb0b413ca35276e43b68ee796366169c1dbde"},
+    {file = "ray-2.35.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:eb86355a3a0e794e2f1dbd5a84805dddfca64921ad0999b7fa5276e40d243692"},
+    {file = "ray-2.35.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7b746913268d5ea5e19bff0eb6bdc7e0538036892a8b57c08411787481195df2"},
+    {file = "ray-2.35.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:e2ccfd144180f03d38b02a81afdac2b437f27e46736bf2653a1f0e8d67ea56cd"},
+    {file = "ray-2.35.0-cp312-cp312-manylinux2014_x86_64.whl", hash = "sha256:2ca1a0de41d4462fd764598a5981cf55fc955599f38f9a1ae10868e94c6dd80d"},
+    {file = "ray-2.35.0-cp312-cp312-win_amd64.whl", hash = "sha256:c5600f745bb0e4df840a5cd51e82b1acf517f73505df9869fe3e369966956129"},
+    {file = "ray-2.35.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:5e98d2bac394b806109782f316740c5b3c3f10a50117c8e28200a528df734928"},
+    {file = "ray-2.35.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c395b46efd0dd871424b1b8d6baf99f91983946fbe351ff66ea34e8919daff29"},
+    {file = "ray-2.35.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:4e6314bfdb8c73abcac13f41cc3d935dd1a8ad94c65005a4bfdc4861dc8b070d"},
+    {file = "ray-2.35.0-cp39-cp39-manylinux2014_x86_64.whl", hash = "sha256:70a154e3071cbb4d7a9b68f2dcf491b96b760be0ec6e2ef11a766071ac6acfef"},
+    {file = "ray-2.35.0-cp39-cp39-win_amd64.whl", hash = "sha256:dd8bdf9d16989684486db9ebcd23679140e2d6769fcdaadc05e8cac6b373023e"},
+]
+
+[package.dependencies]
+aiosignal = "*"
+click = ">=7.0"
+filelock = "*"
+frozenlist = "*"
+fsspec = {version = "*", optional = true, markers = "extra == \"tune\""}
+jsonschema = "*"
+msgpack = ">=1.0.0,<2.0.0"
+packaging = "*"
+pandas = {version = "*", optional = true, markers = "extra == \"tune\""}
+protobuf = ">=3.15.3,<3.19.5 || >3.19.5"
+pyarrow = {version = ">=6.0.1", optional = true, markers = "extra == \"tune\""}
+pyyaml = "*"
+requests = "*"
+tensorboardX = {version = ">=1.9", optional = true, markers = "extra == \"tune\""}
+
+[package.extras]
+adag = ["cupy-cuda12x"]
+air = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "fastapi", "fsspec", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "memray", "numpy (>=1.20)", "opencensus", "pandas", "pandas (>=1.3)", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pyarrow (>=6.0.1)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "requests", "smart-open", "starlette", "tensorboardX (>=1.9)", "uvicorn[standard]", "virtualenv (>=20.0.24,!=20.21.1)", "watchfiles"]
+all = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "cupy-cuda12x", "dm-tree", "fastapi", "fsspec", "grpcio (!=1.56.0)", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "gymnasium (==0.28.1)", "lz4", "memray", "numpy (>=1.20)", "opencensus", "opentelemetry-api", "opentelemetry-exporter-otlp", "opentelemetry-sdk", "pandas", "pandas (>=1.3)", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pyarrow (>=6.0.1)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "pyyaml", "requests", "rich", "scikit-image", "scipy", "smart-open", "starlette", "tensorboardX (>=1.9)", "typer", "uvicorn[standard]", "virtualenv (>=20.0.24,!=20.21.1)", "watchfiles"]
+all-cpp = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "cupy-cuda12x", "dm-tree", "fastapi", "fsspec", "grpcio (!=1.56.0)", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "gymnasium (==0.28.1)", "lz4", "memray", "numpy (>=1.20)", "opencensus", "opentelemetry-api", "opentelemetry-exporter-otlp", "opentelemetry-sdk", "pandas", "pandas (>=1.3)", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pyarrow (>=6.0.1)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "pyyaml", "ray-cpp (==2.35.0)", "requests", "rich", "scikit-image", "scipy", "smart-open", "starlette", "tensorboardX (>=1.9)", "typer", "uvicorn[standard]", "virtualenv (>=20.0.24,!=20.21.1)", "watchfiles"]
+client = ["grpcio (!=1.56.0)"]
+cpp = ["ray-cpp (==2.35.0)"]
+data = ["fsspec", "numpy (>=1.20)", "pandas (>=1.3)", "pyarrow (>=6.0.1)"]
+default = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "memray", "opencensus", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "requests", "smart-open", "virtualenv (>=20.0.24,!=20.21.1)"]
+observability = ["opentelemetry-api", "opentelemetry-exporter-otlp", "opentelemetry-sdk"]
+rllib = ["dm-tree", "fsspec", "gymnasium (==0.28.1)", "lz4", "pandas", "pyarrow (>=6.0.1)", "pyyaml", "requests", "rich", "scikit-image", "scipy", "tensorboardX (>=1.9)", "typer"]
+serve = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "fastapi", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "memray", "opencensus", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "requests", "smart-open", "starlette", "uvicorn[standard]", "virtualenv (>=20.0.24,!=20.21.1)", "watchfiles"]
+serve-grpc = ["aiohttp (>=3.7)", "aiohttp-cors", "colorful", "fastapi", "grpcio (>=1.32.0)", "grpcio (>=1.42.0)", "memray", "opencensus", "prometheus-client (>=0.7.1)", "py-spy (>=0.2.0)", "pydantic (<2.0.dev0 || >=2.5.dev0,<3)", "requests", "smart-open", "starlette", "uvicorn[standard]", "virtualenv (>=20.0.24,!=20.21.1)", "watchfiles"]
+train = ["fsspec", "pandas", "pyarrow (>=6.0.1)", "requests", "tensorboardX (>=1.9)"]
+tune = ["fsspec", "pandas", "pyarrow (>=6.0.1)", "requests", "tensorboardX (>=1.9)"]
+
 [[package]]
 name = "regex"
 version = "2023.5.5"
@@ -3929,6 +4150,138 @@ files = [
 [package.dependencies]
 pyasn1 = ">=0.1.3"
 
+[[package]]
+name = "safetensors"
+version = "0.4.5"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "safetensors-0.4.5-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:a63eaccd22243c67e4f2b1c3e258b257effc4acd78f3b9d397edc8cf8f1298a7"},
+    {file = "safetensors-0.4.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:23fc9b4ec7b602915cbb4ec1a7c1ad96d2743c322f20ab709e2c35d1b66dad27"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6885016f34bef80ea1085b7e99b3c1f92cb1be78a49839203060f67b40aee761"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:133620f443450429322f238fda74d512c4008621227fccf2f8cf4a76206fea7c"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4fb3e0609ec12d2a77e882f07cced530b8262027f64b75d399f1504ffec0ba56"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0f1dd769f064adc33831f5e97ad07babbd728427f98e3e1db6902e369122737"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c6d156bdb26732feada84f9388a9f135528c1ef5b05fae153da365ad4319c4c5"},
+    {file = "safetensors-0.4.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:9e347d77e2c77eb7624400ccd09bed69d35c0332f417ce8c048d404a096c593b"},
+    {file = "safetensors-0.4.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9f556eea3aec1d3d955403159fe2123ddd68e880f83954ee9b4a3f2e15e716b6"},
+    {file = "safetensors-0.4.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9483f42be3b6bc8ff77dd67302de8ae411c4db39f7224dec66b0eb95822e4163"},
+    {file = "safetensors-0.4.5-cp310-none-win32.whl", hash = "sha256:7389129c03fadd1ccc37fd1ebbc773f2b031483b04700923c3511d2a939252cc"},
+    {file = "safetensors-0.4.5-cp310-none-win_amd64.whl", hash = "sha256:e98ef5524f8b6620c8cdef97220c0b6a5c1cef69852fcd2f174bb96c2bb316b1"},
+    {file = "safetensors-0.4.5-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:21f848d7aebd5954f92538552d6d75f7c1b4500f51664078b5b49720d180e47c"},
+    {file = "safetensors-0.4.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bb07000b19d41e35eecef9a454f31a8b4718a185293f0d0b1c4b61d6e4487971"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:09dedf7c2fda934ee68143202acff6e9e8eb0ddeeb4cfc24182bef999efa9f42"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:59b77e4b7a708988d84f26de3ebead61ef1659c73dcbc9946c18f3b1786d2688"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5d3bc83e14d67adc2e9387e511097f254bd1b43c3020440e708858c684cbac68"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:39371fc551c1072976073ab258c3119395294cf49cdc1f8476794627de3130df"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6c19feda32b931cae0acd42748a670bdf56bee6476a046af20181ad3fee4090"},
+    {file = "safetensors-0.4.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a659467495de201e2f282063808a41170448c78bada1e62707b07a27b05e6943"},
+    {file = "safetensors-0.4.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bad5e4b2476949bcd638a89f71b6916fa9a5cae5c1ae7eede337aca2100435c0"},
+    {file = "safetensors-0.4.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a3a315a6d0054bc6889a17f5668a73f94f7fe55121ff59e0a199e3519c08565f"},
+    {file = "safetensors-0.4.5-cp311-none-win32.whl", hash = "sha256:a01e232e6d3d5cf8b1667bc3b657a77bdab73f0743c26c1d3c5dd7ce86bd3a92"},
+    {file = "safetensors-0.4.5-cp311-none-win_amd64.whl", hash = "sha256:cbd39cae1ad3e3ef6f63a6f07296b080c951f24cec60188378e43d3713000c04"},
+    {file = "safetensors-0.4.5-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:473300314e026bd1043cef391bb16a8689453363381561b8a3e443870937cc1e"},
+    {file = "safetensors-0.4.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:801183a0f76dc647f51a2d9141ad341f9665602a7899a693207a82fb102cc53e"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1524b54246e422ad6fb6aea1ac71edeeb77666efa67230e1faf6999df9b2e27f"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b3139098e3e8b2ad7afbca96d30ad29157b50c90861084e69fcb80dec7430461"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65573dc35be9059770808e276b017256fa30058802c29e1038eb1c00028502ea"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fd33da8e9407559f8779c82a0448e2133737f922d71f884da27184549416bfed"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3685ce7ed036f916316b567152482b7e959dc754fcc4a8342333d222e05f407c"},
+    {file = "safetensors-0.4.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:dde2bf390d25f67908278d6f5d59e46211ef98e44108727084d4637ee70ab4f1"},
+    {file = "safetensors-0.4.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7469d70d3de970b1698d47c11ebbf296a308702cbaae7fcb993944751cf985f4"},
+    {file = "safetensors-0.4.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3a6ba28118636a130ccbb968bc33d4684c48678695dba2590169d5ab03a45646"},
+    {file = "safetensors-0.4.5-cp312-none-win32.whl", hash = "sha256:c859c7ed90b0047f58ee27751c8e56951452ed36a67afee1b0a87847d065eec6"},
+    {file = "safetensors-0.4.5-cp312-none-win_amd64.whl", hash = "sha256:b5a8810ad6a6f933fff6c276eae92c1da217b39b4d8b1bc1c0b8af2d270dc532"},
+    {file = "safetensors-0.4.5-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:25e5f8e2e92a74f05b4ca55686234c32aac19927903792b30ee6d7bd5653d54e"},
+    {file = "safetensors-0.4.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:81efb124b58af39fcd684254c645e35692fea81c51627259cdf6d67ff4458916"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:585f1703a518b437f5103aa9cf70e9bd437cb78eea9c51024329e4fb8a3e3679"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4b99fbf72e3faf0b2f5f16e5e3458b93b7d0a83984fe8d5364c60aa169f2da89"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b17b299ca9966ca983ecda1c0791a3f07f9ca6ab5ded8ef3d283fff45f6bcd5f"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:76ded72f69209c9780fdb23ea89e56d35c54ae6abcdec67ccb22af8e696e449a"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2783956926303dcfeb1de91a4d1204cd4089ab441e622e7caee0642281109db3"},
+    {file = "safetensors-0.4.5-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d94581aab8c6b204def4d7320f07534d6ee34cd4855688004a4354e63b639a35"},
+    {file = "safetensors-0.4.5-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:67e1e7cb8678bb1b37ac48ec0df04faf689e2f4e9e81e566b5c63d9f23748523"},
+    {file = "safetensors-0.4.5-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:dbd280b07e6054ea68b0cb4b16ad9703e7d63cd6890f577cb98acc5354780142"},
+    {file = "safetensors-0.4.5-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:77d9b228da8374c7262046a36c1f656ba32a93df6cc51cd4453af932011e77f1"},
+    {file = "safetensors-0.4.5-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:500cac01d50b301ab7bb192353317035011c5ceeef0fca652f9f43c000bb7f8d"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:75331c0c746f03158ded32465b7d0b0e24c5a22121743662a2393439c43a45cf"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:670e95fe34e0d591d0529e5e59fd9d3d72bc77b1444fcaa14dccda4f36b5a38b"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:098923e2574ff237c517d6e840acada8e5b311cb1fa226019105ed82e9c3b62f"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:13ca0902d2648775089fa6a0c8fc9e6390c5f8ee576517d33f9261656f851e3f"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5f0032bedc869c56f8d26259fe39cd21c5199cd57f2228d817a0e23e8370af25"},
+    {file = "safetensors-0.4.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f4b15f51b4f8f2a512341d9ce3475cacc19c5fdfc5db1f0e19449e75f95c7dc8"},
+    {file = "safetensors-0.4.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:f6594d130d0ad933d885c6a7b75c5183cb0e8450f799b80a39eae2b8508955eb"},
+    {file = "safetensors-0.4.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:60c828a27e852ded2c85fc0f87bf1ec20e464c5cd4d56ff0e0711855cc2e17f8"},
+    {file = "safetensors-0.4.5-cp37-none-win32.whl", hash = "sha256:6d3de65718b86c3eeaa8b73a9c3d123f9307a96bbd7be9698e21e76a56443af5"},
+    {file = "safetensors-0.4.5-cp37-none-win_amd64.whl", hash = "sha256:5a2d68a523a4cefd791156a4174189a4114cf0bf9c50ceb89f261600f3b2b81a"},
+    {file = "safetensors-0.4.5-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:e7a97058f96340850da0601a3309f3d29d6191b0702b2da201e54c6e3e44ccf0"},
+    {file = "safetensors-0.4.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:63bfd425e25f5c733f572e2246e08a1c38bd6f2e027d3f7c87e2e43f228d1345"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3664ac565d0e809b0b929dae7ccd74e4d3273cd0c6d1220c6430035befb678e"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:313514b0b9b73ff4ddfb4edd71860696dbe3c1c9dc4d5cc13dbd74da283d2cbf"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:31fa33ee326f750a2f2134a6174773c281d9a266ccd000bd4686d8021f1f3dac"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:09566792588d77b68abe53754c9f1308fadd35c9f87be939e22c623eaacbed6b"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:309aaec9b66cbf07ad3a2e5cb8a03205663324fea024ba391594423d0f00d9fe"},
+    {file = "safetensors-0.4.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:53946c5813b8f9e26103c5efff4a931cc45d874f45229edd68557ffb35ffb9f8"},
+    {file = "safetensors-0.4.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:868f9df9e99ad1e7f38c52194063a982bc88fedc7d05096f4f8160403aaf4bd6"},
+    {file = "safetensors-0.4.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:9cc9449bd0b0bc538bd5e268221f0c5590bc5c14c1934a6ae359d44410dc68c4"},
+    {file = "safetensors-0.4.5-cp38-none-win32.whl", hash = "sha256:83c4f13a9e687335c3928f615cd63a37e3f8ef072a3f2a0599fa09f863fb06a2"},
+    {file = "safetensors-0.4.5-cp38-none-win_amd64.whl", hash = "sha256:b98d40a2ffa560653f6274e15b27b3544e8e3713a44627ce268f419f35c49478"},
+    {file = "safetensors-0.4.5-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:cf727bb1281d66699bef5683b04d98c894a2803442c490a8d45cd365abfbdeb2"},
+    {file = "safetensors-0.4.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:96f1d038c827cdc552d97e71f522e1049fef0542be575421f7684756a748e457"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:139fbee92570ecea774e6344fee908907db79646d00b12c535f66bc78bd5ea2c"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c36302c1c69eebb383775a89645a32b9d266878fab619819ce660309d6176c9b"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d641f5b8149ea98deb5ffcf604d764aad1de38a8285f86771ce1abf8e74c4891"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b4db6a61d968de73722b858038c616a1bebd4a86abe2688e46ca0cc2d17558f2"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b75a616e02f21b6f1d5785b20cecbab5e2bd3f6358a90e8925b813d557666ec1"},
+    {file = "safetensors-0.4.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:788ee7d04cc0e0e7f944c52ff05f52a4415b312f5efd2ee66389fb7685ee030c"},
+    {file = "safetensors-0.4.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:87bc42bd04fd9ca31396d3ca0433db0be1411b6b53ac5a32b7845a85d01ffc2e"},
+    {file = "safetensors-0.4.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4037676c86365a721a8c9510323a51861d703b399b78a6b4486a54a65a975fca"},
+    {file = "safetensors-0.4.5-cp39-none-win32.whl", hash = "sha256:1500418454529d0ed5c1564bda376c4ddff43f30fce9517d9bee7bcce5a8ef50"},
+    {file = "safetensors-0.4.5-cp39-none-win_amd64.whl", hash = "sha256:9d1a94b9d793ed8fe35ab6d5cea28d540a46559bafc6aae98f30ee0867000cab"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fdadf66b5a22ceb645d5435a0be7a0292ce59648ca1d46b352f13cff3ea80410"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d42ffd4c2259f31832cb17ff866c111684c87bd930892a1ba53fed28370c918c"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd8a1f6d2063a92cd04145c7fd9e31a1c7d85fbec20113a14b487563fdbc0597"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:951d2fcf1817f4fb0ef0b48f6696688a4e852a95922a042b3f96aaa67eedc920"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6ac85d9a8c1af0e3132371d9f2d134695a06a96993c2e2f0bbe25debb9e3f67a"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e3cec4a29eb7fe8da0b1c7988bc3828183080439dd559f720414450de076fcab"},
+    {file = "safetensors-0.4.5-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:21742b391b859e67b26c0b2ac37f52c9c0944a879a25ad2f9f9f3cd61e7fda8f"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c7db3006a4915151ce1913652e907cdede299b974641a83fbc092102ac41b644"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f68bf99ea970960a237f416ea394e266e0361895753df06e3e06e6ea7907d98b"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8158938cf3324172df024da511839d373c40fbfaa83e9abf467174b2910d7b4c"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:540ce6c4bf6b58cb0fd93fa5f143bc0ee341c93bb4f9287ccd92cf898cc1b0dd"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:bfeaa1a699c6b9ed514bd15e6a91e74738b71125a9292159e3d6b7f0a53d2cde"},
+    {file = "safetensors-0.4.5-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:01c8f00da537af711979e1b42a69a8ec9e1d7112f208e0e9b8a35d2c381085ef"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a0dd565f83b30f2ca79b5d35748d0d99dd4b3454f80e03dfb41f0038e3bdf180"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:023b6e5facda76989f4cba95a861b7e656b87e225f61811065d5c501f78cdb3f"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9633b663393d5796f0b60249549371e392b75a0b955c07e9c6f8708a87fc841f"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78dd8adfb48716233c45f676d6e48534d34b4bceb50162c13d1f0bdf6f78590a"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8e8deb16c4321d61ae72533b8451ec4a9af8656d1c61ff81aa49f966406e4b68"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:52452fa5999dc50c4decaf0c53aa28371f7f1e0fe5c2dd9129059fbe1e1599c7"},
+    {file = "safetensors-0.4.5-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d5f23198821e227cfc52d50fa989813513db381255c6d100927b012f0cfec63d"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:f4beb84b6073b1247a773141a6331117e35d07134b3bb0383003f39971d414bb"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:68814d599d25ed2fdd045ed54d370d1d03cf35e02dce56de44c651f828fb9b7b"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f0b6453c54c57c1781292c46593f8a37254b8b99004c68d6c3ce229688931a22"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:adaa9c6dead67e2dd90d634f89131e43162012479d86e25618e821a03d1eb1dc"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:73e7d408e9012cd17511b382b43547850969c7979efc2bc353f317abaf23c84c"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:775409ce0fcc58b10773fdb4221ed1eb007de10fe7adbdf8f5e8a56096b6f0bc"},
+    {file = "safetensors-0.4.5-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:834001bed193e4440c4a3950a31059523ee5090605c907c66808664c932b549c"},
+    {file = "safetensors-0.4.5.tar.gz", hash = "sha256:d73de19682deabb02524b3d5d1f8b3aaba94c72f1bbfc7911b9b9d5d391c0310"},
+]
+
+[package.extras]
+all = ["safetensors[jax]", "safetensors[numpy]", "safetensors[paddlepaddle]", "safetensors[pinned-tf]", "safetensors[quality]", "safetensors[testing]", "safetensors[torch]"]
+dev = ["safetensors[all]"]
+jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[numpy]"]
+mlx = ["mlx (>=0.0.9)"]
+numpy = ["numpy (>=1.21.6)"]
+paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"]
+pinned-tf = ["safetensors[numpy]", "tensorflow (==2.11.0)"]
+quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
+tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"]
+testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
+torch = ["safetensors[numpy]", "torch (>=1.10)"]
+
 [[package]]
 name = "scikit-learn"
 version = "1.2.2"
@@ -4015,24 +4368,24 @@ test = ["Cython", "array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "me
 
 [[package]]
 name = "seaborn"
-version = "0.12.2"
+version = "0.13.2"
 description = "Statistical data visualization"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "seaborn-0.12.2-py3-none-any.whl", hash = "sha256:ebf15355a4dba46037dfd65b7350f014ceb1f13c05e814eda2c9f5fd731afc08"},
-    {file = "seaborn-0.12.2.tar.gz", hash = "sha256:374645f36509d0dcab895cba5b47daf0586f77bfe3b36c97c607db7da5be0139"},
+    {file = "seaborn-0.13.2-py3-none-any.whl", hash = "sha256:636f8336facf092165e27924f223d3c62ca560b1f2bb5dff7ab7fad265361987"},
+    {file = "seaborn-0.13.2.tar.gz", hash = "sha256:93e60a40988f4d65e9f4885df477e2fdaff6b73a9ded434c1ab356dd57eefff7"},
 ]
 
 [package.dependencies]
-matplotlib = ">=3.1,<3.6.1 || >3.6.1"
-numpy = ">=1.17,<1.24.0 || >1.24.0"
-pandas = ">=0.25"
+matplotlib = ">=3.4,<3.6.1 || >3.6.1"
+numpy = ">=1.20,<1.24.0 || >1.24.0"
+pandas = ">=1.2"
 
 [package.extras]
 dev = ["flake8", "flit", "mypy", "pandas-stubs", "pre-commit", "pytest", "pytest-cov", "pytest-xdist"]
-docs = ["ipykernel", "nbconvert", "numpydoc", "pydata_sphinx_theme (==0.10.0rc2)", "pyyaml", "sphinx-copybutton", "sphinx-design", "sphinx-issues"]
-stats = ["scipy (>=1.3)", "statsmodels (>=0.10)"]
+docs = ["ipykernel", "nbconvert", "numpydoc", "pydata_sphinx_theme (==0.10.0rc2)", "pyyaml", "sphinx (<6.0.0)", "sphinx-copybutton", "sphinx-design", "sphinx-issues"]
+stats = ["scipy (>=1.7)", "statsmodels (>=0.12)"]
 
 [[package]]
 name = "setuptools"
@@ -4136,6 +4489,93 @@ files = [
     {file = "soupsieve-2.4.1.tar.gz", hash = "sha256:89d12b2d5dfcd2c9e8c22326da9d9aa9cb3dfab0a83a024f05704076ee8d35ea"},
 ]
 
+[[package]]
+name = "sqlalchemy"
+version = "2.0.34"
+description = "Database Abstraction Library"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:95d0b2cf8791ab5fb9e3aa3d9a79a0d5d51f55b6357eecf532a120ba3b5524db"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:243f92596f4fd4c8bd30ab8e8dd5965afe226363d75cab2468f2c707f64cd83b"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9ea54f7300553af0a2a7235e9b85f4204e1fc21848f917a3213b0e0818de9a24"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:173f5f122d2e1bff8fbd9f7811b7942bead1f5e9f371cdf9e670b327e6703ebd"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:196958cde924a00488e3e83ff917be3b73cd4ed8352bbc0f2989333176d1c54d"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:bd90c221ed4e60ac9d476db967f436cfcecbd4ef744537c0f2d5291439848768"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-win32.whl", hash = "sha256:3166dfff2d16fe9be3241ee60ece6fcb01cf8e74dd7c5e0b64f8e19fab44911b"},
+    {file = "SQLAlchemy-2.0.34-cp310-cp310-win_amd64.whl", hash = "sha256:6831a78bbd3c40f909b3e5233f87341f12d0b34a58f14115c9e94b4cdaf726d3"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c7db3db284a0edaebe87f8f6642c2b2c27ed85c3e70064b84d1c9e4ec06d5d84"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:430093fce0efc7941d911d34f75a70084f12f6ca5c15d19595c18753edb7c33b"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79cb400c360c7c210097b147c16a9e4c14688a6402445ac848f296ade6283bbc"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb1b30f31a36c7f3fee848391ff77eebdd3af5750bf95fbf9b8b5323edfdb4ec"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8fddde2368e777ea2a4891a3fb4341e910a056be0bb15303bf1b92f073b80c02"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:80bd73ea335203b125cf1d8e50fef06be709619eb6ab9e7b891ea34b5baa2287"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-win32.whl", hash = "sha256:6daeb8382d0df526372abd9cb795c992e18eed25ef2c43afe518c73f8cccb721"},
+    {file = "SQLAlchemy-2.0.34-cp311-cp311-win_amd64.whl", hash = "sha256:5bc08e75ed11693ecb648b7a0a4ed80da6d10845e44be0c98c03f2f880b68ff4"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:53e68b091492c8ed2bd0141e00ad3089bcc6bf0e6ec4142ad6505b4afe64163e"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bcd18441a49499bf5528deaa9dee1f5c01ca491fc2791b13604e8f972877f812"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:165bbe0b376541092bf49542bd9827b048357f4623486096fc9aaa6d4e7c59a2"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c3330415cd387d2b88600e8e26b510d0370db9b7eaf984354a43e19c40df2e2b"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:97b850f73f8abbffb66ccbab6e55a195a0eb655e5dc74624d15cff4bfb35bd74"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7cee4c6917857fd6121ed84f56d1dc78eb1d0e87f845ab5a568aba73e78adf83"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-win32.whl", hash = "sha256:fbb034f565ecbe6c530dff948239377ba859420d146d5f62f0271407ffb8c580"},
+    {file = "SQLAlchemy-2.0.34-cp312-cp312-win_amd64.whl", hash = "sha256:707c8f44931a4facd4149b52b75b80544a8d824162602b8cd2fe788207307f9a"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:24af3dc43568f3780b7e1e57c49b41d98b2d940c1fd2e62d65d3928b6f95f021"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e60ed6ef0a35c6b76b7640fe452d0e47acc832ccbb8475de549a5cc5f90c2c06"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:413c85cd0177c23e32dee6898c67a5f49296640041d98fddb2c40888fe4daa2e"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:25691f4adfb9d5e796fd48bf1432272f95f4bbe5f89c475a788f31232ea6afba"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:526ce723265643dbc4c7efb54f56648cc30e7abe20f387d763364b3ce7506c82"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-win32.whl", hash = "sha256:13be2cc683b76977a700948411a94c67ad8faf542fa7da2a4b167f2244781cf3"},
+    {file = "SQLAlchemy-2.0.34-cp37-cp37m-win_amd64.whl", hash = "sha256:e54ef33ea80d464c3dcfe881eb00ad5921b60f8115ea1a30d781653edc2fd6a2"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:43f28005141165edd11fbbf1541c920bd29e167b8bbc1fb410d4fe2269c1667a"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b68094b165a9e930aedef90725a8fcfafe9ef95370cbb54abc0464062dbf808f"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6a1e03db964e9d32f112bae36f0cc1dcd1988d096cfd75d6a588a3c3def9ab2b"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:203d46bddeaa7982f9c3cc693e5bc93db476ab5de9d4b4640d5c99ff219bee8c"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:ae92bebca3b1e6bd203494e5ef919a60fb6dfe4d9a47ed2453211d3bd451b9f5"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:9661268415f450c95f72f0ac1217cc6f10256f860eed85c2ae32e75b60278ad8"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-win32.whl", hash = "sha256:895184dfef8708e15f7516bd930bda7e50ead069280d2ce09ba11781b630a434"},
+    {file = "SQLAlchemy-2.0.34-cp38-cp38-win_amd64.whl", hash = "sha256:6e7cde3a2221aa89247944cafb1b26616380e30c63e37ed19ff0bba5e968688d"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:dbcdf987f3aceef9763b6d7b1fd3e4ee210ddd26cac421d78b3c206d07b2700b"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ce119fc4ce0d64124d37f66a6f2a584fddc3c5001755f8a49f1ca0a177ef9796"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a17d8fac6df9835d8e2b4c5523666e7051d0897a93756518a1fe101c7f47f2f0"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ebc11c54c6ecdd07bb4efbfa1554538982f5432dfb8456958b6d46b9f834bb7"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:2e6965346fc1491a566e019a4a1d3dfc081ce7ac1a736536367ca305da6472a8"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:220574e78ad986aea8e81ac68821e47ea9202b7e44f251b7ed8c66d9ae3f4278"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-win32.whl", hash = "sha256:b75b00083e7fe6621ce13cfce9d4469c4774e55e8e9d38c305b37f13cf1e874c"},
+    {file = "SQLAlchemy-2.0.34-cp39-cp39-win_amd64.whl", hash = "sha256:c29d03e0adf3cc1a8c3ec62d176824972ae29b67a66cbb18daff3062acc6faa8"},
+    {file = "SQLAlchemy-2.0.34-py3-none-any.whl", hash = "sha256:7286c353ee6475613d8beff83167374006c6b3e3f0e6491bfe8ca610eb1dec0f"},
+    {file = "sqlalchemy-2.0.34.tar.gz", hash = "sha256:10d8f36990dd929690666679b0f42235c159a7051534adb135728ee52828dd22"},
+]
+
+[package.dependencies]
+greenlet = {version = "!=0.4.17", markers = "python_version < \"3.13\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\")"}
+typing-extensions = ">=4.6.0"
+
+[package.extras]
+aiomysql = ["aiomysql (>=0.2.0)", "greenlet (!=0.4.17)"]
+aioodbc = ["aioodbc", "greenlet (!=0.4.17)"]
+aiosqlite = ["aiosqlite", "greenlet (!=0.4.17)", "typing_extensions (!=3.10.0.1)"]
+asyncio = ["greenlet (!=0.4.17)"]
+asyncmy = ["asyncmy (>=0.2.3,!=0.2.4,!=0.2.6)", "greenlet (!=0.4.17)"]
+mariadb-connector = ["mariadb (>=1.0.1,!=1.1.2,!=1.1.5)"]
+mssql = ["pyodbc"]
+mssql-pymssql = ["pymssql"]
+mssql-pyodbc = ["pyodbc"]
+mypy = ["mypy (>=0.910)"]
+mysql = ["mysqlclient (>=1.4.0)"]
+mysql-connector = ["mysql-connector-python"]
+oracle = ["cx_oracle (>=8)"]
+oracle-oracledb = ["oracledb (>=1.0.1)"]
+postgresql = ["psycopg2 (>=2.7)"]
+postgresql-asyncpg = ["asyncpg", "greenlet (!=0.4.17)"]
+postgresql-pg8000 = ["pg8000 (>=1.29.1)"]
+postgresql-psycopg = ["psycopg (>=3.0.7)"]
+postgresql-psycopg2binary = ["psycopg2-binary"]
+postgresql-psycopg2cffi = ["psycopg2cffi"]
+postgresql-psycopgbinary = ["psycopg[binary] (>=3.0.7)"]
+pymysql = ["pymysql"]
+sqlcipher = ["sqlcipher3_binary"]
+
 [[package]]
 name = "stack-data"
 version = "0.6.2"
@@ -4157,30 +4597,36 @@ tests = ["cython", "littleutils", "pygments", "pytest", "typeguard"]
 
 [[package]]
 name = "statsforecast"
-version = "1.5.0"
+version = "1.7.6"
 description = "Time series forecasting suite using statistical models"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "statsforecast-1.5.0-py3-none-any.whl", hash = "sha256:fafe3c7170af59b51d720b67b6c8046ed95a474242d07bdd44070dfdde28e9c4"},
-    {file = "statsforecast-1.5.0.tar.gz", hash = "sha256:3196e52908d8a2439d732dc49f4d3f0ae9c5993be23622ccedd152b1671be802"},
+    {file = "statsforecast-1.7.6-py3-none-any.whl", hash = "sha256:a9d39ef0303788063562737912db79c84047177c9b2ac68a9c95c36d7b499028"},
+    {file = "statsforecast-1.7.6.tar.gz", hash = "sha256:fd956802e72039d9ac8833cfe693dbeef90c939132bf56984d312a2866fbd8ce"},
 ]
 
 [package.dependencies]
+cloudpickle = "*"
+coreforecast = ">=0.0.12"
 fugue = ">=0.8.1"
-matplotlib = "*"
 numba = ">=0.55.0"
 numpy = ">=1.21.6"
 pandas = ">=1.3.5"
-plotly = "*"
-plotly-resampler = "*"
 scipy = ">=1.7.3"
 statsmodels = ">=0.13.2"
+threadpoolctl = "*"
 tqdm = "*"
+utilsforecast = ">=0.1.4"
 
 [package.extras]
-dev = ["black", "datasetsforecast", "flake8", "fugue (>=0.7.0)", "fugue[dask] (>=0.8.1)", "matplotlib", "mypy", "nbdev", "neuralforecast", "pmdarima", "prophet", "protobuf (>=3.15.3,<4.0.0)", "ray", "scikit-learn"]
-ray = ["fugue[ray] (>=0.8.1)", "protobuf (>=3.15.3,<4.0.0)"]
+all = ["black", "datasetsforecast", "fire", "fugue[dask] (>=0.8.1)", "fugue[ray] (>=0.8.1)", "fugue[spark] (>=0.8.1)", "nbdev", "nbdev-plotly", "nbformat", "numpy (<2)", "pandas (<2.2)", "pandas[plot]", "plotly", "plotly-resampler", "pmdarima", "polars[numpy]", "pre-commit", "prophet", "protobuf (>=3.15.3,<4.0.0)", "pyarrow", "ray (<2.8)", "scikit-learn", "setuptools (<70)", "supersmoother"]
+dask = ["fugue[dask] (>=0.8.1)"]
+dev = ["black", "datasetsforecast", "fire", "nbdev", "nbdev-plotly", "nbformat", "pandas[plot]", "pmdarima", "polars[numpy]", "pre-commit", "prophet", "pyarrow", "scikit-learn", "setuptools (<70)", "supersmoother"]
+plotly = ["plotly", "plotly-resampler"]
+polars = ["polars[numpy]"]
+ray = ["fugue[ray] (>=0.8.1)", "numpy (<2)", "pandas (<2.2)", "protobuf (>=3.15.3,<4.0.0)", "ray (<2.8)"]
+spark = ["fugue[spark] (>=0.8.1)"]
 
 [[package]]
 name = "statsmodels"
@@ -4291,20 +4737,6 @@ scipy = "*"
 [package.extras]
 dev = ["pip-tools", "pytest", "rpy2"]
 
-[[package]]
-name = "tenacity"
-version = "8.2.2"
-description = "Retry code until it succeeds"
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "tenacity-8.2.2-py3-none-any.whl", hash = "sha256:2f277afb21b851637e8f52e6a613ff08734c347dc19ade928e519d7d2d8569b0"},
-    {file = "tenacity-8.2.2.tar.gz", hash = "sha256:43af037822bd0029025877f3b2d97cc4d7bb0c2991000a3d59d71517c5c969e0"},
-]
-
-[package.extras]
-doc = ["reno", "sphinx", "tornado (>=4.5)"]
-
 [[package]]
 name = "tensorboard"
 version = "2.15.1"
@@ -4386,6 +4818,123 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["flake8", "isort", "pytest"]
 
+[[package]]
+name = "tokenizers"
+version = "0.19.1"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tokenizers-0.19.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:952078130b3d101e05ecfc7fc3640282d74ed26bcf691400f872563fca15ac97"},
+    {file = "tokenizers-0.19.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:82c8b8063de6c0468f08e82c4e198763e7b97aabfe573fd4cf7b33930ca4df77"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f03727225feaf340ceeb7e00604825addef622d551cbd46b7b775ac834c1e1c4"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:453e4422efdfc9c6b6bf2eae00d5e323f263fff62b29a8c9cd526c5003f3f642"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02e81bf089ebf0e7f4df34fa0207519f07e66d8491d963618252f2e0729e0b46"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b07c538ba956843833fee1190cf769c60dc62e1cf934ed50d77d5502194d63b1"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e28cab1582e0eec38b1f38c1c1fb2e56bce5dc180acb1724574fc5f47da2a4fe"},
+    {file = "tokenizers-0.19.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b01afb7193d47439f091cd8f070a1ced347ad0f9144952a30a41836902fe09e"},
+    {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:7fb297edec6c6841ab2e4e8f357209519188e4a59b557ea4fafcf4691d1b4c98"},
+    {file = "tokenizers-0.19.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2e8a3dd055e515df7054378dc9d6fa8c8c34e1f32777fb9a01fea81496b3f9d3"},
+    {file = "tokenizers-0.19.1-cp310-none-win32.whl", hash = "sha256:7ff898780a155ea053f5d934925f3902be2ed1f4d916461e1a93019cc7250837"},
+    {file = "tokenizers-0.19.1-cp310-none-win_amd64.whl", hash = "sha256:bea6f9947e9419c2fda21ae6c32871e3d398cba549b93f4a65a2d369662d9403"},
+    {file = "tokenizers-0.19.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:5c88d1481f1882c2e53e6bb06491e474e420d9ac7bdff172610c4f9ad3898059"},
+    {file = "tokenizers-0.19.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ddf672ed719b4ed82b51499100f5417d7d9f6fb05a65e232249268f35de5ed14"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:dadc509cc8a9fe460bd274c0e16ac4184d0958117cf026e0ea8b32b438171594"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfedf31824ca4915b511b03441784ff640378191918264268e6923da48104acc"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ac11016d0a04aa6487b1513a3a36e7bee7eec0e5d30057c9c0408067345c48d2"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:76951121890fea8330d3a0df9a954b3f2a37e3ec20e5b0530e9a0044ca2e11fe"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b342d2ce8fc8d00f376af068e3274e2e8649562e3bc6ae4a67784ded6b99428d"},
+    {file = "tokenizers-0.19.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d16ff18907f4909dca9b076b9c2d899114dd6abceeb074eca0c93e2353f943aa"},
+    {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:706a37cc5332f85f26efbe2bdc9ef8a9b372b77e4645331a405073e4b3a8c1c6"},
+    {file = "tokenizers-0.19.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:16baac68651701364b0289979ecec728546133e8e8fe38f66fe48ad07996b88b"},
+    {file = "tokenizers-0.19.1-cp311-none-win32.whl", hash = "sha256:9ed240c56b4403e22b9584ee37d87b8bfa14865134e3e1c3fb4b2c42fafd3256"},
+    {file = "tokenizers-0.19.1-cp311-none-win_amd64.whl", hash = "sha256:ad57d59341710b94a7d9dbea13f5c1e7d76fd8d9bcd944a7a6ab0b0da6e0cc66"},
+    {file = "tokenizers-0.19.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:621d670e1b1c281a1c9698ed89451395d318802ff88d1fc1accff0867a06f153"},
+    {file = "tokenizers-0.19.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d924204a3dbe50b75630bd16f821ebda6a5f729928df30f582fb5aade90c818a"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4f3fefdc0446b1a1e6d81cd4c07088ac015665d2e812f6dbba4a06267d1a2c95"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9620b78e0b2d52ef07b0d428323fb34e8ea1219c5eac98c2596311f20f1f9266"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:04ce49e82d100594715ac1b2ce87d1a36e61891a91de774755f743babcd0dd52"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5c2ff13d157afe413bf7e25789879dd463e5a4abfb529a2d8f8473d8042e28f"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3174c76efd9d08f836bfccaca7cfec3f4d1c0a4cf3acbc7236ad577cc423c840"},
+    {file = "tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c9d5b6c0e7a1e979bec10ff960fae925e947aab95619a6fdb4c1d8ff3708ce3"},
+    {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a179856d1caee06577220ebcfa332af046d576fb73454b8f4d4b0ba8324423ea"},
+    {file = "tokenizers-0.19.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:952b80dac1a6492170f8c2429bd11fcaa14377e097d12a1dbe0ef2fb2241e16c"},
+    {file = "tokenizers-0.19.1-cp312-none-win32.whl", hash = "sha256:01d62812454c188306755c94755465505836fd616f75067abcae529c35edeb57"},
+    {file = "tokenizers-0.19.1-cp312-none-win_amd64.whl", hash = "sha256:b70bfbe3a82d3e3fb2a5e9b22a39f8d1740c96c68b6ace0086b39074f08ab89a"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:bb9dfe7dae85bc6119d705a76dc068c062b8b575abe3595e3c6276480e67e3f1"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:1f0360cbea28ea99944ac089c00de7b2e3e1c58f479fb8613b6d8d511ce98267"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:71e3ec71f0e78780851fef28c2a9babe20270404c921b756d7c532d280349214"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b82931fa619dbad979c0ee8e54dd5278acc418209cc897e42fac041f5366d626"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e8ff5b90eabdcdaa19af697885f70fe0b714ce16709cf43d4952f1f85299e73a"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e742d76ad84acbdb1a8e4694f915fe59ff6edc381c97d6dfdd054954e3478ad4"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d8c5d59d7b59885eab559d5bc082b2985555a54cda04dda4c65528d90ad252ad"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b2da5c32ed869bebd990c9420df49813709e953674c0722ff471a116d97b22d"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:638e43936cc8b2cbb9f9d8dde0fe5e7e30766a3318d2342999ae27f68fdc9bd6"},
+    {file = "tokenizers-0.19.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:78e769eb3b2c79687d9cb0f89ef77223e8e279b75c0a968e637ca7043a84463f"},
+    {file = "tokenizers-0.19.1-cp37-none-win32.whl", hash = "sha256:72791f9bb1ca78e3ae525d4782e85272c63faaef9940d92142aa3eb79f3407a3"},
+    {file = "tokenizers-0.19.1-cp37-none-win_amd64.whl", hash = "sha256:f3bbb7a0c5fcb692950b041ae11067ac54826204318922da754f908d95619fbc"},
+    {file = "tokenizers-0.19.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:07f9295349bbbcedae8cefdbcfa7f686aa420be8aca5d4f7d1ae6016c128c0c5"},
+    {file = "tokenizers-0.19.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:10a707cc6c4b6b183ec5dbfc5c34f3064e18cf62b4a938cb41699e33a99e03c1"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6309271f57b397aa0aff0cbbe632ca9d70430839ca3178bf0f06f825924eca22"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ad23d37d68cf00d54af184586d79b84075ada495e7c5c0f601f051b162112dc"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:427c4f0f3df9109314d4f75b8d1f65d9477033e67ffaec4bca53293d3aca286d"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e83a31c9cf181a0a3ef0abad2b5f6b43399faf5da7e696196ddd110d332519ee"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c27b99889bd58b7e301468c0838c5ed75e60c66df0d4db80c08f43462f82e0d3"},
+    {file = "tokenizers-0.19.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bac0b0eb952412b0b196ca7a40e7dce4ed6f6926489313414010f2e6b9ec2adf"},
+    {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8a6298bde623725ca31c9035a04bf2ef63208d266acd2bed8c2cb7d2b7d53ce6"},
+    {file = "tokenizers-0.19.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:08a44864e42fa6d7d76d7be4bec62c9982f6f6248b4aa42f7302aa01e0abfd26"},
+    {file = "tokenizers-0.19.1-cp38-none-win32.whl", hash = "sha256:1de5bc8652252d9357a666e609cb1453d4f8e160eb1fb2830ee369dd658e8975"},
+    {file = "tokenizers-0.19.1-cp38-none-win_amd64.whl", hash = "sha256:0bcce02bf1ad9882345b34d5bd25ed4949a480cf0e656bbd468f4d8986f7a3f1"},
+    {file = "tokenizers-0.19.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:0b9394bd204842a2a1fd37fe29935353742be4a3460b6ccbaefa93f58a8df43d"},
+    {file = "tokenizers-0.19.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4692ab92f91b87769d950ca14dbb61f8a9ef36a62f94bad6c82cc84a51f76f6a"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6258c2ef6f06259f70a682491c78561d492e885adeaf9f64f5389f78aa49a051"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c85cf76561fbd01e0d9ea2d1cbe711a65400092bc52b5242b16cfd22e51f0c58"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:670b802d4d82bbbb832ddb0d41df7015b3e549714c0e77f9bed3e74d42400fbe"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:85aa3ab4b03d5e99fdd31660872249df5e855334b6c333e0bc13032ff4469c4a"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cbf001afbbed111a79ca47d75941e9e5361297a87d186cbfc11ed45e30b5daba"},
+    {file = "tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4c89aa46c269e4e70c4d4f9d6bc644fcc39bb409cb2a81227923404dd6f5227"},
+    {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:39c1ec76ea1027438fafe16ecb0fb84795e62e9d643444c1090179e63808c69d"},
+    {file = "tokenizers-0.19.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c2a0d47a89b48d7daa241e004e71fb5a50533718897a4cd6235cb846d511a478"},
+    {file = "tokenizers-0.19.1-cp39-none-win32.whl", hash = "sha256:61b7fe8886f2e104d4caf9218b157b106207e0f2a4905c9c7ac98890688aabeb"},
+    {file = "tokenizers-0.19.1-cp39-none-win_amd64.whl", hash = "sha256:f97660f6c43efd3e0bfd3f2e3e5615bf215680bad6ee3d469df6454b8c6e8256"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3b11853f17b54c2fe47742c56d8a33bf49ce31caf531e87ac0d7d13d327c9334"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d26194ef6c13302f446d39972aaa36a1dda6450bc8949f5eb4c27f51191375bd"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:e8d1ed93beda54bbd6131a2cb363a576eac746d5c26ba5b7556bc6f964425594"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca407133536f19bdec44b3da117ef0d12e43f6d4b56ac4c765f37eca501c7bda"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce05fde79d2bc2e46ac08aacbc142bead21614d937aac950be88dc79f9db9022"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:35583cd46d16f07c054efd18b5d46af4a2f070a2dd0a47914e66f3ff5efb2b1e"},
+    {file = "tokenizers-0.19.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:43350270bfc16b06ad3f6f07eab21f089adb835544417afda0f83256a8bf8b75"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b4399b59d1af5645bcee2072a463318114c39b8547437a7c2d6a186a1b5a0e2d"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6852c5b2a853b8b0ddc5993cd4f33bfffdca4fcc5d52f89dd4b8eada99379285"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bcd266ae85c3d39df2f7e7d0e07f6c41a55e9a3123bb11f854412952deacd828"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ecb2651956eea2aa0a2d099434134b1b68f1c31f9a5084d6d53f08ed43d45ff2"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:b279ab506ec4445166ac476fb4d3cc383accde1ea152998509a94d82547c8e2a"},
+    {file = "tokenizers-0.19.1-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:89183e55fb86e61d848ff83753f64cded119f5d6e1f553d14ffee3700d0a4a49"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:b2edbc75744235eea94d595a8b70fe279dd42f3296f76d5a86dde1d46e35f574"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:0e64bfde9a723274e9a71630c3e9494ed7b4c0f76a1faacf7fe294cd26f7ae7c"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0b5ca92bfa717759c052e345770792d02d1f43b06f9e790ca0a1db62838816f3"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f8a20266e695ec9d7a946a019c1d5ca4eddb6613d4f466888eee04f16eedb85"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63c38f45d8f2a2ec0f3a20073cccb335b9f99f73b3c69483cd52ebc75369d8a1"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dd26e3afe8a7b61422df3176e06664503d3f5973b94f45d5c45987e1cb711876"},
+    {file = "tokenizers-0.19.1-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:eddd5783a4a6309ce23432353cdb36220e25cbb779bfa9122320666508b44b88"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:56ae39d4036b753994476a1b935584071093b55c7a72e3b8288e68c313ca26e7"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:f9939ca7e58c2758c01b40324a59c034ce0cebad18e0d4563a9b1beab3018243"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6c330c0eb815d212893c67a032e9dc1b38a803eccb32f3e8172c19cc69fbb439"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec11802450a2487cdf0e634b750a04cbdc1c4d066b97d94ce7dd2cb51ebb325b"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2b718f316b596f36e1dae097a7d5b91fc5b85e90bf08b01ff139bd8953b25af"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ed69af290c2b65169f0ba9034d1dc39a5db9459b32f1dd8b5f3f32a3fcf06eab"},
+    {file = "tokenizers-0.19.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f8a9c828277133af13f3859d1b6bf1c3cb6e9e1637df0e45312e6b7c2e622b1f"},
+    {file = "tokenizers-0.19.1.tar.gz", hash = "sha256:ee59e6680ed0fdbe6b724cf38bd70400a0c1dd623b07ac729087270caeac88e3"},
+]
+
+[package.dependencies]
+huggingface-hub = ">=0.16.4,<1.0"
+
+[package.extras]
+dev = ["tokenizers[testing]"]
+docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
+testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests", "ruff"]
+
 [[package]]
 name = "toml"
 version = "0.10.2"
@@ -4447,6 +4996,27 @@ typing-extensions = "*"
 [package.extras]
 opt-einsum = ["opt-einsum (>=3.3)"]
 
+[[package]]
+name = "torch-tb-profiler"
+version = "0.4.3"
+description = "PyTorch Profiler TensorBoard Plugin"
+optional = false
+python-versions = ">=3.6.2"
+files = [
+    {file = "torch_tb_profiler-0.4.3-py3-none-any.whl", hash = "sha256:207a49b05572dd983e4ab29eb5e0fcadd60374a8f93c78ec638217e8d18788dc"},
+    {file = "torch_tb_profiler-0.4.3.tar.gz", hash = "sha256:8b8d29b2de960b3c4423087b23cec29beaf9ac3a8c7b046c18fd25b218f726b1"},
+]
+
+[package.dependencies]
+pandas = ">=1.0.0"
+tensorboard = ">=1.15,<2.1.0 || >2.1.0"
+
+[package.extras]
+blob = ["azure-storage-blob"]
+gs = ["google-cloud-storage"]
+hdfs = ["fsspec", "pyarrow"]
+s3 = ["boto3"]
+
 [[package]]
 name = "torchcde"
 version = "0.2.5"
@@ -4650,6 +5220,74 @@ files = [
     {file = "trampoline-0.1.2-py3-none-any.whl", hash = "sha256:36cc9a4ff9811843d177fc0e0740efbd7da39eadfe6e50c9e2937cbc06d899d9"},
 ]
 
+[[package]]
+name = "transformers"
+version = "4.44.2"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "transformers-4.44.2-py3-none-any.whl", hash = "sha256:1c02c65e7bfa5e52a634aff3da52138b583fc6f263c1f28d547dc144ba3d412d"},
+    {file = "transformers-4.44.2.tar.gz", hash = "sha256:36aa17cc92ee154058e426d951684a2dab48751b35b49437896f898931270826"},
+]
+
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.23.2,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+safetensors = ">=0.4.1"
+tokenizers = ">=0.19,<0.20"
+tqdm = ">=4.27"
+
+[package.extras]
+accelerate = ["accelerate (>=0.21.0)"]
+agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"]
+all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"]
+audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+benchmark = ["optimum-benchmark (>=0.2.0)"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"]
+deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"]
+dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm (<=0.9.16)", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"]
+flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"]
+ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+natten = ["natten (>=0.14.6,<0.15.0)"]
+onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
+onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+optuna = ["optuna"]
+quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.5.1)", "urllib3 (<2.0.0)"]
+ray = ["ray[tune] (>=2.7.0)"]
+retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
+ruff = ["ruff (==0.5.1)"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"]
+serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
+sigopt = ["sigopt"]
+sklearn = ["scikit-learn"]
+speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.5.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+tf = ["keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<0.24)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+timm = ["timm (<=0.9.16)"]
+tokenizers = ["tokenizers (>=0.19,<0.20)"]
+torch = ["accelerate (>=0.21.0)", "torch"]
+torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"]
+torchhub = ["filelock", "huggingface-hub (>=0.23.2,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"]
+video = ["av (==9.2.0)", "decord (==0.6.0)"]
+vision = ["Pillow (>=10.0.1,<=15.0)"]
+
 [[package]]
 name = "triad"
 version = "0.9.8"
@@ -4696,91 +5334,6 @@ scipy = ">=1.11.3,<2.0.0"
 strenum = ">=0.4.9,<0.5.0"
 torch = ">=1.13.1"
 
-[[package]]
-name = "tsdownsample"
-version = "0.1.3"
-description = "Time series downsampling in rust"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "tsdownsample-0.1.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:e1e8b04a17efb6f25a730467bedd0a1ceda165149707305309f9456041cf4e49"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1791225e0e610b8c883fd7c8237756901bd10af42240a98e747bdb1085ee4f7e"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c1cfb42437732825af4b4fd6964ba8632c3b7a8094648ea9fb940412c62973ae"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:721ae2a9a385e36fe688d43c877852ba0bab2056b6875cf86aee1d6dec8b567c"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:66941f131ec096478483fdd9a80a408a12a0c01c85b0ebf9eb41445c2721eca6"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_24_armv7l.whl", hash = "sha256:0bce3ae95aa104ec0fbc4c37db5694ad3fa9bd09f5509f49215de157b78a99b2"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_24_ppc64le.whl", hash = "sha256:bab1f0258f41cff4f3968076946ff468641f2b6c32c624a278c2cdf47a5b3eff"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-manylinux_2_24_s390x.whl", hash = "sha256:d8d41957d44593c8fee21f89454303db9a9eb2cf0e556c0138c84157702b39a4"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:6ef3ad8f8f0fac177bab09fe2e916034d8d3d64e1b0531f2b3df9ecc1b36f84b"},
-    {file = "tsdownsample-0.1.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:e268741155eff05125bd45f5ab32fd20daed293503c3749765eafab8fe3e12ef"},
-    {file = "tsdownsample-0.1.3-cp310-none-win32.whl", hash = "sha256:0cf6695ecf63ab7114a18ebeb12f722811ec455842391ac216bb698803abdaeb"},
-    {file = "tsdownsample-0.1.3-cp310-none-win_amd64.whl", hash = "sha256:d5493f021f96db43e35a37bca70ac13460e49de264085643b1bac88c136574d3"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:539bae2e1675af94c26c8eed67f1bb8ebfc72fe44fa17965fb324ef38cb9e70d"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f547ad4b796097d314fdc5538c50db8b073b110aae13e540cd8db4802b0317f6"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:8762d057a1b335fe44eec345b36b4d3b68ed369ca1214724a1c376546f49dce9"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ec8f06d6ad9f26a52b34f229ed5647ee3a2d373014a1c29903e1d57208b7ded"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08ed25561d504aad77ba815e4d176efe80a37b8761a53bf77bb087e08ae8f54b"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_24_armv7l.whl", hash = "sha256:757b62df7fa170ada3748f2ee6682948be9bbd83370dba4bf83929dfd98570a3"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_24_ppc64le.whl", hash = "sha256:c5d0ab1a46caf68764c36e6749d56d3c02ab39eb2f61ad700d8369dfe2861ad5"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-manylinux_2_24_s390x.whl", hash = "sha256:8d5bdcf9e09ee58411299ed5d47b1e9cdfaab61a8293cc2167af0e666aafcd4c"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0884215aae9b75107f3400b43800ce7b61ce573e2f19e8fb155fbd2918b0d0b3"},
-    {file = "tsdownsample-0.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4deb0c331cb95ee634b6bd605b44e7936d5bf50e22f4efda15fa719ddf181951"},
-    {file = "tsdownsample-0.1.3-cp311-none-win32.whl", hash = "sha256:3f0b70794d6ae79efc213ab4c384bbd3404b700c508d3873bbe63db3c48ab156"},
-    {file = "tsdownsample-0.1.3-cp311-none-win_amd64.whl", hash = "sha256:f97a858a855d7d84c96d3b89daa2237c80da8da12ff7a3a3d13e029d6c15e69d"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:0822465103cde9688ecbbdad6642f3415871479bd62682bf85a55f0d156482c0"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:bb4ad7c0fea8267156e14c0c1a8f027b5c0831e9067a436b7888c1085e569aac"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4eab94d2e392470e6e26bebdcbd7e600ad1e0edca4f88c160ed8e72e280c87aa"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58788587348e88064bfdb88acbb1d51078c5b1fff934ed1433355d1dbf939641"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d59c184cac10edae160b1908c9ee579345033aaefe455581f5bd4375caada0b"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_24_armv7l.whl", hash = "sha256:35b0eb80cd5d1eaacab1818b6fa3374a815787c844e385fc57f29785714a357b"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_24_ppc64le.whl", hash = "sha256:acd0bae11eb3777e47de41783b590c1d0f6bc25c85870cb8a5d9fd47797f3f8d"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-manylinux_2_24_s390x.whl", hash = "sha256:09d705fe7a5a73aa97a486dbef8ed4b0b9a59e679ad2189eb9923c02c1321000"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:76107f22e01135bc97f493083c623bab88c12a79b909ee931efa585f6543d3c9"},
-    {file = "tsdownsample-0.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a966c97138809f2c3fe627b3acfa041983123342f92f9782d4573d16155d6c77"},
-    {file = "tsdownsample-0.1.3-cp312-none-win32.whl", hash = "sha256:63b730c96a539abd71863166c203310383b0f04b268e935e69fd68a2b7a4d27a"},
-    {file = "tsdownsample-0.1.3-cp312-none-win_amd64.whl", hash = "sha256:55479a6e1b1fa60092b6d344a99d374ccba57a40d23f9fd4d2fcdd5faabf7d40"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:3caa8906b87efa2277584dde851f214db4a3aa4d6d5c631b0ec40e7978271ac8"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:982c4e885785f261d500c2d36f7054544313d0caacfc53c63fc47571f28194f3"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:fe138a297a504b2121c56e32afb2e645028177faef1a5152a3b080fe932bd458"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3157795be6fbd2de9e936a242aa7c00ce8ab2def12fdec49d74502a216b403e"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e069bcf40b0ebf80d9f3a7f827cf26c60dde9b1474268a27e54f37daade1017d"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_24_armv7l.whl", hash = "sha256:5dd63a6a5358f52257775c83f66111fcdbd07cf70603a7d6271f5783b70bfaef"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_24_ppc64le.whl", hash = "sha256:5d77f9fd7d69a44e0935ad5f32a02b76b53c9aed325824565948b2a0bb6d2e08"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-manylinux_2_24_s390x.whl", hash = "sha256:c4fa2115a8f46ff2d99958cd6652db84d09f4a1ac7cbafb62288e300df528b48"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9bc4d095c43947f6499603210270e1dd29919b9fb692655acbd5b1e7d7667102"},
-    {file = "tsdownsample-0.1.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a1f89a77976f2cd24b19fa15dd98fa1aec2acef83743d9d9e31bc5daad7de8a3"},
-    {file = "tsdownsample-0.1.3-cp37-none-win32.whl", hash = "sha256:9afe1856a18cbd58726614805cac01b2a7259a8f31396413e7c3c0629fe1f72c"},
-    {file = "tsdownsample-0.1.3-cp37-none-win_amd64.whl", hash = "sha256:213d10479f06e98bb351bcf2f9b6b2c58632f6e4d27e200f224e7379b93775c2"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:c22103ec83b363b9195cb62533ddf76eaff7b198014a4dd40a8d1a0a2e8c6fa7"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:85a703c2d29dd0c7923b5b7d3c0eccc639a4087fbe8d0a0290506abcb8ef48bf"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6ccff0710fb2dac229f810877cb308087f1456610f1aa272524b69f551642ee2"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a198ab5f2ce1c9d30077b13393295dfbecaaddee6d2b5ffee7439d454c108f3"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:468752a26958c12a95ce583f46347e0c3eacb579323c3a230af27d50c3cabac5"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_24_armv7l.whl", hash = "sha256:5293167ece8428f664ecd69302ecda32a6ad635d9aff6c21d1796198169e56bc"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_24_ppc64le.whl", hash = "sha256:23557544e1d8e767606b134b55c5c598bcc368d73ba904ff4fe91b93d8935531"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-manylinux_2_24_s390x.whl", hash = "sha256:e0791339d9b8ddb78d1082a31ae880d00e4fa375147b8f2fdebc0915782e38ee"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:51d7a39b60d622f12beb1c04b404c7ab7743653eb74089b9663504675a9bfc62"},
-    {file = "tsdownsample-0.1.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:9f2ba2ad61db5ef9617b1d6e764e9aabde63a391b1c8ee97098d348a9b9d883a"},
-    {file = "tsdownsample-0.1.3-cp38-none-win32.whl", hash = "sha256:e69e6d066c30e946aeb7c19ae7d2364ee6f1a072c8e47dee76825d86b5ad84be"},
-    {file = "tsdownsample-0.1.3-cp38-none-win_amd64.whl", hash = "sha256:9491a03ec700ad5ca0f555553b4da9b8285fc461c28f7970a61acf6b05d8f3ad"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:23d3b2d24b36fa5d05bf7e2e2748565522f3c8afd29a706dbb22a8c6b2dc4a75"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1715fa981e5406c0c7adef04cdcc4b1a4c88e422946dc104b82f1669605c6da7"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5a44a101a1b7fa6b67d185a9f905bc0a9e0dcac6537b653a71f14dce71a451fa"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:372b09627f39899b90605bd71ac481a9052f135b8c96d431255c3af6c383d0d4"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac2d1141b0c3899bac018a6d8ed4b1baca2fb88ba8d8c9c7b1a4116f548c11a8"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_24_armv7l.whl", hash = "sha256:ab6e9780f5a9d64b4692ac70f9a0aaf5a7bd499bc82e56b15e42e1a40e9f24a1"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_24_ppc64le.whl", hash = "sha256:dc348f7802e18c33a6d8e0386debfa92ffa679591551fece9f2d49c0501b5c35"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-manylinux_2_24_s390x.whl", hash = "sha256:0d67e05dc61002c9672582f516ecf9473a6eba710be8580e9c9f37b187d83762"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c1fb3e646206593ee92630e27a725cf00a9e70e20af5a7032baa3de2d2943bc6"},
-    {file = "tsdownsample-0.1.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:20bf49fec6a4371fd417ca75a4096bafce2a3d3263a89f89d5bfba70bd78e409"},
-    {file = "tsdownsample-0.1.3-cp39-none-win32.whl", hash = "sha256:74854a1b0c0a7a6581402769de12559cd9efeb1bb12ace831701aacfc0ddc140"},
-    {file = "tsdownsample-0.1.3-cp39-none-win_amd64.whl", hash = "sha256:4d25567c0f15ca9e3f9d822934f60e5258e23a06d5515d12617518dc9f99f26f"},
-    {file = "tsdownsample-0.1.3.tar.gz", hash = "sha256:5268d0ab5e8572138871feff389440a0c59d5e0fe02c0fa1cf975d74ba33b933"},
-]
-
-[package.dependencies]
-numpy = "*"
-
 [[package]]
 name = "typing-extensions"
 version = "4.6.0"
@@ -4820,6 +5373,27 @@ secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]
 
+[[package]]
+name = "utilsforecast"
+version = "0.2.4"
+description = "Forecasting utilities"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "utilsforecast-0.2.4-py3-none-any.whl", hash = "sha256:f4357aaec9757e79ffbadad5318e0aa067c57ea51a4802b71d630761adf73f0b"},
+    {file = "utilsforecast-0.2.4.tar.gz", hash = "sha256:72f07adb99c6cd638322832bc0229d6d0e3acd97ac4c94cd832bc012ac4ef0cf"},
+]
+
+[package.dependencies]
+numpy = "*"
+packaging = "*"
+pandas = ">=1.1.1"
+
+[package.extras]
+dev = ["black", "datasetsforecast (==0.0.8)", "nbdev (<2.3.26)", "numba (>=0.58.0)", "pandas[plot]", "plotly", "plotly-resampler", "polars[numpy]", "pyarrow", "scipy"]
+plotting = ["pandas[plot]", "plotly", "plotly-resampler"]
+polars = ["polars[numpy]"]
+
 [[package]]
 name = "validators"
 version = "0.20.0"
@@ -4964,6 +5538,24 @@ files = [
 [package.extras]
 dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
 
+[[package]]
+name = "window-ops"
+version = "0.0.15"
+description = "Implementations of window operations such as rolling and expanding."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "window_ops-0.0.15-py3-none-any.whl", hash = "sha256:7dbd18b467939ac5db3f6834c07e7ffb723691f5d86c22a39e707713d8ac86e3"},
+    {file = "window_ops-0.0.15.tar.gz", hash = "sha256:3c762d35a38d562f34cda33a272ced2c8d5dd88bd050c13bc82a592cf668a535"},
+]
+
+[package.dependencies]
+numba = "*"
+numpy = "*"
+
+[package.extras]
+dev = ["pandas"]
+
 [[package]]
 name = "xarray"
 version = "2023.5.0"
@@ -5015,6 +5607,22 @@ plotting = ["graphviz", "matplotlib"]
 pyspark = ["cloudpickle", "pyspark", "scikit-learn"]
 scikit-learn = ["scikit-learn"]
 
+[[package]]
+name = "xlrd"
+version = "2.0.1"
+description = "Library for developers to extract data from Microsoft Excel (tm) .xls spreadsheet files"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+files = [
+    {file = "xlrd-2.0.1-py2.py3-none-any.whl", hash = "sha256:6a33ee89877bd9abc1158129f6e94be74e2679636b8a205b43b85206c3f0bbdd"},
+    {file = "xlrd-2.0.1.tar.gz", hash = "sha256:f72f148f54442c6b056bf931dbc34f986fd0c3b0b6b5a58d013c9aef274d0c88"},
+]
+
+[package.extras]
+build = ["twine", "wheel"]
+docs = ["sphinx"]
+test = ["pytest", "pytest-cov"]
+
 [[package]]
 name = "yarl"
 version = "1.9.2"
@@ -5179,4 +5787,4 @@ test = ["pytest"]
 [metadata]
 lock-version = "2.0"
 python-versions = "3.10.14"
-content-hash = "ffb8beb4d46281b17458164647d4e8ec089859d92a1d244596b7175e2aefe19a"
+content-hash = "baa1b583c7a216cb2f5355350efc7aeca7e0a0b861acba108eaf386ffb09736c"
diff --git a/pyproject.toml b/pyproject.toml
index e433eeab..953322c5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -30,7 +30,7 @@ jupytext = "^1.15.2"
 
 
 [tool.poetry.group.visualization.dependencies]
-seaborn = "^0.12.2"
+seaborn = "^0.13.2"
 
 
 [tool.poetry.group.data.dependencies]
@@ -43,6 +43,18 @@ lightning = "^2.1.2"
 tensorboard = "^2.15.1"
 torchmetrics = "^1.2.0"
 torchdyn = "^1.0.6"
+torch-tb-profiler = "^0.4.3"
+
+
+[tool.poetry.group.nixtla.dependencies]
+neuralforecast = "^1.7.4"
+mlforecast = "^0.13.4"
+statsforecast = "^1.7.6"
+datasetsforecast = "^0.0.8"
+
+
+[tool.poetry.group.huggingface.dependencies]
+transformers = "^4.44.2"
 
 [build-system]
 requires = ["poetry-core"]