[DOCS] fix remaining broken links (#1499)

deven367 · web-flow · commit 9bc90c1eac5b · 2026-04-08T09:40:34.000-04:00
diff --git a/docs/models.html.md b/docs/models.html.md
@@ -46,7 +46,7 @@ Recurrent neural networks for sequential forecasting:
 Attention-based architectures for capturing complex temporal patterns:
 
 - `AutoTFT`: [Temporal Fusion Transformer with multi-horizon forecasting](./models.tft.html)
-- `AutoVanillaTransformer`: [Standard transformer architecture](./models.vanillatransformer.hml)
+- `AutoVanillaTransformer`: [Standard transformer architecture](./models.vanillatransformer.html)
 - `AutoInformer`: [Efficient transformer for long sequence forecasting](./models.informer.html)
 - `AutoAutoformer`: [Auto-correlation based transformer](./models.autoformer.html)
 - `AutoFEDformer`: [Frequency enhanced decomposition transformer](./models.fedformer.html)
@@ -160,7 +160,7 @@ from neuralforecast.auto import AutoHINT
 from neuralforecast.models.nhits import NHITS
 from ray import tune
 
-# Perform a conjunct hyperparameter optimization with 
+# Perform a conjunct hyperparameter optimization with
 # NHITS + HINT reconciliation configurations
 nhits_config = {
        "learning_rate": tune.choice([1e-3]),                                     # Initial Learning rate
diff --git a/nbs/docs/capabilities/cross_validation.ipynb b/nbs/docs/capabilities/cross_validation.ipynb
@@ -8,7 +8,7 @@
     "\n",
     ":::{.callout-warning collapse=\"true\"}\n",
     "## Prerequesites\n",
-    "This Guide assumes basic familiarity with NeuralForecast. For a minimal example visit the [Quick Start](../getting-started/02_quickstart.ipynb)\n",
+    "This Guide assumes basic familiarity with NeuralForecast. For a minimal example visit the [Quick Start](../getting-started/quickstart.html)\n",
     ":::\n",
     "\n",
     "To measure the performance of a forecasting model, we can assess its performance on historical data using *cross-validation*.\n",
diff --git a/nbs/docs/capabilities/exogenous_variables.ipynb b/nbs/docs/capabilities/exogenous_variables.ipynb
@@ -41,7 +41,7 @@
    "metadata": {},
    "source": [
     ":::{.callout-important}\n",
-    "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/02_quickstart.ipynb) guide.\n",
+    "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/quickstart.html) guide.\n",
     ":::"
    ]
   },
diff --git a/nbs/docs/capabilities/objectives.ipynb b/nbs/docs/capabilities/objectives.ipynb
@@ -17,7 +17,7 @@
     "\n",
     "| Scale-Dependent                                              | Percentage-Errors                                                     | Scale-Independent                                              | Robust                                                 |\n",
     "|:-------------------------------------------------------------|:----------------------------------------------------------------------|:---------------------------------------------------------------|:-------------------------------------------------------|\n",
-    "|[**MAE**](../../losses.pytorch.html#mae)       |[**MAPE**](../../losses.pytorch.html#mape)   |[**MASE**](../../losses.pytorch.html#mase)|[**Huber**](../losses.pytorch#class-huberloss)            |\n",
+    "|[**MAE**](../../losses.pytorch.html#mae)       |[**MAPE**](../../losses.pytorch.html#mape)   |[**MASE**](../../losses.pytorch.html#mase)|[**Huber**](../../losses.pytorch.html#huber-loss)            |\n",
     "|[**MSE**](../../losses.pytorch.html#mse)        |[**sMAPE**](../../losses.pytorch.html#smape)                 |                                                                |[**Tukey**](../../losses.pytorch.html#tukeyloss)            |\n",
     "|[**RMSE**](../../losses.pytorch.html#rmse) |                                                                       |                                                                |[**HuberMQLoss**](../../losses.pytorch.html#hubermqloss)|\n",
     "\n",
diff --git a/nbs/docs/capabilities/save_load_models.ipynb b/nbs/docs/capabilities/save_load_models.ipynb
@@ -26,7 +26,7 @@
    "metadata": {},
    "source": [
     ":::{.callout-important}\n",
-    "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/02_quickstart.ipynb) guide.\n",
+    "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/quickstart.html) guide.\n",
     ":::"
    ]
   },
diff --git a/nbs/docs/getting-started/introduction.ipynb b/nbs/docs/getting-started/introduction.ipynb
@@ -37,7 +37,7 @@
     "* **Train and Evaluation Losses** Scale-dependent, percentage and scale independent errors, and parametric likelihoods.\n",
     "* **Automatic Model Selection** Parallelized automatic hyperparameter tuning, that efficiently searches best validation configuration.\n",
     "* **Simple Interface** Unified SKLearn Interface for `StatsForecast` and `MLForecast` compatibility.\n",
-    "* **Model Collection**: Out of the box implementation of `MLP`, `LSTM`, `RNN`, `TCN`, `DilatedRNN`, `NBEATS`, `NHITS`, `ESRNN`, `Informer`, `TFT`, `PatchTST`, `VanillaTransformer`, `StemGNN` and `HINT`. See the entire [collection here](../capabilities/01_overview)."
+    "* **Model Collection**: Out of the box implementation of `MLP`, `LSTM`, `RNN`, `TCN`, `DilatedRNN`, `NBEATS`, `NHITS`, `ESRNN`, `Informer`, `TFT`, `PatchTST`, `VanillaTransformer`, `StemGNN` and `HINT`. See the entire [collection here](../capabilities/overview.html)."
    ]
   },
   {
diff --git a/nbs/docs/getting-started/quickstart.ipynb b/nbs/docs/getting-started/quickstart.ipynb
@@ -14,7 +14,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This notebook provides an example on how to start using the main functionalities of the NeuralForecast library. The `NeuralForecast` class allows users to easily interact with `NeuralForecast.models` PyTorch models. In this example we will forecast AirPassengers data with a classic `LSTM` and the recent `NHITS` models. The full list of available models is available [here](../capabilities/01_overview).\n"
+    "This notebook provides an example on how to start using the main functionalities of the NeuralForecast library. The `NeuralForecast` class allows users to easily interact with `NeuralForecast.models` PyTorch models. In this example we will forecast AirPassengers data with a classic `LSTM` and the recent `NHITS` models. The full list of available models is available [here]( ../capabilities/overview.html).\n"
    ]
   },
   {
@@ -412,7 +412,7 @@
    "metadata": {},
    "source": [
     ":::{.callout-tip}\n",
-    "For this guide we are using a simple `LSTM` model. More recent models, such as `TSMixer`, `TFT` and `NHITS` achieve better accuracy than `LSTM` in most settings. The full list of available models is available [here](../capabilities/01_overview).\n",
+    "For this guide we are using a simple `LSTM` model. More recent models, such as `TSMixer`, `TFT` and `NHITS` achieve better accuracy than `LSTM` in most settings. The full list of available models is available [here]( ../capabilities/overview.html).\n",
     ":::"
    ]
   },
diff --git a/nbs/docs/tutorials/comparing_methods.ipynb b/nbs/docs/tutorials/comparing_methods.ipynb
@@ -160,8 +160,8 @@
     "# The 'demand' becomes 'y' representing the target variable we want to forecast\n",
     "Y_df = Y_df.rename(\n",
     "    columns={\n",
-    "        'item_id': 'unique_id', \n",
-    "        'timestamp': 'ds', \n",
+    "        'item_id': 'unique_id',\n",
+    "        'timestamp': 'ds',\n",
     "        'demand': 'y'\n",
     "    }\n",
     ")\n",
@@ -431,7 +431,7 @@
     "# Get the current time before forecasting starts, this will be used to measure the execution time\n",
     "init = time()\n",
     "\n",
-    "# Call the forecast method of the StatsForecast instance to predict the next 28 days (h=28) \n",
+    "# Call the forecast method of the StatsForecast instance to predict the next 28 days (h=28)\n",
     "fcst_df = sf.forecast(df=Y_df, h=28)\n",
     "\n",
     "# Get the current time after the forecasting ends\n",
@@ -1267,7 +1267,7 @@
     "plot_series(\n",
     "    Y_df,\n",
     "    fcst_df,\n",
-    "    max_insample_length=28 * 3, \n",
+    "    max_insample_length=28 * 3,\n",
     "    models=['CrostonOptimized', 'AutoNHITS', 'SeasonalNaive', 'LGBMRegressor'],\n",
     ")"
    ]
@@ -1519,7 +1519,7 @@
    "source": [
     "init = time()\n",
     "cv_mlf_df = mlf.cross_validation(\n",
-    "    df=Y_df, \n",
+    "    df=Y_df,\n",
     "    h=horizon,\n",
     "    n_windows=3,\n",
     ")\n",
@@ -1897,9 +1897,9 @@
     "for cutoff in cutoffs:\n",
     "    display(\n",
     "        plot_series(\n",
-    "            Y_df, \n",
-    "            cv_df.query('cutoff == @cutoff').drop(columns=['y', 'cutoff']), \n",
-    "            max_insample_length=28 * 5, \n",
+    "            Y_df,\n",
+    "            cv_df.query('cutoff == @cutoff').drop(columns=['y', 'cutoff']),\n",
+    "            max_insample_length=28 * 5,\n",
     "            ids=['FOODS_3_001_CA_1'],\n",
     "        )\n",
     "    )"
@@ -1976,7 +1976,7 @@
     "for cutoff in cutoffs:\n",
     "    display(\n",
     "        plot_series(\n",
-    "            agg_Y_df, \n",
+    "            agg_Y_df,\n",
     "            agg_cv_df.query('cutoff == @cutoff').drop(columns=['y', 'cutoff']),\n",
     "            max_insample_length=28 * 5,\n",
     "        )\n",
@@ -2649,8 +2649,8 @@
    "source": [
     "plot_series(\n",
     "    Y_df,\n",
-    "    cv_df.drop(columns=['cutoff', 'y']), \n",
-    "    max_insample_length=28 * 6, \n",
+    "    cv_df.drop(columns=['cutoff', 'y']),\n",
+    "    max_insample_length=28 * 6,\n",
     "    models=['AutoNHITS'],\n",
     ")"
    ]
@@ -2716,12 +2716,12 @@
    "id": "1394e95e-b65c-45d6-aea0-55e9e1940b60",
    "metadata": {},
    "source": [
-    "- [Available Models StatsForecast](../../../statsforecast/models)\n",
-    "- [Available Models NeuralForecast](../capabilities/01_overview)\n",
-    "- [Loss Functions in NeuralForecast](../capabilities/02_objectives)\n",
-    "- [Getting Started NeuralForecast](../getting-started/02_quickstart)\n",
-    "- [Hierarchical Reconciliation](../../../hierarchicalforecast/examples/TourismSmall)\n",
-    "- [Distributed ML Forecast (trees)](../../../mlforecast/docs/getting-started/quick_start_distributed)\n",
+    "- [Available Models StatsForecast](../../../statsforecast/models.html)\n",
+    "- [Available Models NeuralForecast]( ../capabilities/overview.html)\n",
+    "- [Loss Functions in NeuralForecast](../capabilities/objectives.html)\n",
+    "- [Getting Started NeuralForecast](../getting-started/quickstart.html)\n",
+    "- [Hierarchical Reconciliation](../../../hierarchicalforecast/examples/tourismsmall.html)\n",
+    "- [Distributed ML Forecast (trees)](../../../mlforecast/docs/getting-started/quick_start_distributed.html)\n",
     "- [Using StatsForecast to train millions of time series](https://www.anyscale.com/blog/how-nixtla-uses-ray-to-accurately-predict-more-than-a-million-time-series)\n",
     "- [Intermittent Demand Forecasting With Nixtla on Databricks](https://www.databricks.com/blog/2022/12/06/intermittent-demand-forecasting-nixtla-databricks.html)"
    ]
diff --git a/nbs/docs/tutorials/cross_validation.ipynb b/nbs/docs/tutorials/cross_validation.ipynb
@@ -40,7 +40,7 @@
    "source": [
     ":::{.callout-warning collapse=\"true\"}\n",
     "## Prerequesites\n",
-    "This guide assumes basic familiarity with `neuralforecast`. For a minimal example visit the [Quick Start](../getting-started/02_quickstart.ipynb)\n",
+    "This guide assumes basic familiarity with `neuralforecast`. For a minimal example visit the [Quick Start](../getting-started/quickstart.html)\n",
     ":::"
    ]
   },
@@ -274,7 +274,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In this tutorial, we will use `neuralforecast's` [MPL](../../models.mlp#class-mlp), [NBEATS](../../models.nbeats#class-nbeats), and [NHITS](../../models.nhits#class-nhits) models. \n",
+    "In this tutorial, we will use `neuralforecast's` [MPL](../../models.mlp.html#mlp-2), [NBEATS](../../models.nbeats.html#nbeats), and [NHITS](../../models.nhits.html#nhits) models. \n",
     "\n",
     "First, we need to create a list of models and then instantiate the `NeuralForecast` class. For each model, we'll define the following hyperparameters:\n",
     "\n",
diff --git a/nbs/docs/tutorials/forecasting_tft.ipynb b/nbs/docs/tutorials/forecasting_tft.ipynb
@@ -538,7 +538,7 @@
     "\n",
     "In Challu et al [2] we demonstrate that the N-HiTS model outperforms the latest transformers by more than 20% with 50 times less computation.\n",
     "\n",
-    "Learn how to use the N-HiTS and the NeuralForecast library in [this tutorial](../use-cases/electricity_peak_forecasting)."
+    "Learn how to use the N-HiTS and the NeuralForecast library in [this tutorial](../use-cases/electricity_peak_forecasting.html)."
    ]
   },
   {
diff --git a/nbs/docs/tutorials/getting_started_complete.ipynb b/nbs/docs/tutorials/getting_started_complete.ipynb
@@ -17,7 +17,7 @@
    "source": [
     ":::{.callout-warning collapse=\"true\"}\n",
     "## Prerequesites\n",
-    "This Guide assumes basic familiarity with NeuralForecast. For a minimal example visit the [Quick Start](../getting-started/02_quickstart.ipynb)\n",
+    "This Guide assumes basic familiarity with NeuralForecast. For a minimal example visit the [Quick Start](../getting-started/quickstart.html)\n",
     ":::\n",
     "\n",
     "Follow this article for a step to step guide on building a production-ready forecasting pipeline for multiple time series. \n",
@@ -42,13 +42,13 @@
     "## Not Covered in this guide\n",
     "\n",
     "* Using external regressors or exogenous variables\n",
-    "    * Follow this tutorial to [include exogenous variables](../capabilities/03_exogenous_variables.ipynb) like weather or holidays or static variables like category or family. \n",
+    "    * Follow this tutorial to [include exogenous variables](../capabilities/exogenous_variables.html) like weather or holidays or static variables like category or family. \n",
     "\n",
     "* Probabilistic forecasting\n",
-    "    * Follow this tutorial to [generate probabilistic forecasts](../tutorials/03_uncertainty_quantification.ipynb)\n",
+    "    * Follow this tutorial to [generate probabilistic forecasts](../tutorials/uncertainty_quantification.html)\n",
     "\n",
     "* Transfer Learning\n",
-    "    * Train a model and use it to forecast on different data using [this tutorial](../tutorials/17_transfer_learning.ipynb)\n",
+    "    * Train a model and use it to forecast on different data using [this tutorial](../tutorials/transfer_learning.html)\n",
     ":::"
    ]
   },
@@ -79,7 +79,7 @@
    "source": [
     "## 1. Install libraries\n",
     "\n",
-    "We assume you have `NeuralForecast` already installed. Check this guide for instructions on [how to install NeuralForecast](../getting-started/04_installation.ipynb)."
+    "We assume you have `NeuralForecast` already installed. Check this guide for instructions on [how to install NeuralForecast](../getting-started/installation.html)."
    ]
   },
   {
diff --git a/nbs/docs/tutorials/hierarchical_forecasting.ipynb b/nbs/docs/tutorials/hierarchical_forecasting.ipynb
@@ -310,7 +310,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We compare against AutoARIMA, a well-established traditional forecasting method from the [StatsForecast](../../../statsforecast/index) package, for which we reconcile the forecasts using [HierarchicalForecast](../../../hierarchicalforecast/index)."
+    "We compare against AutoARIMA, a well-established traditional forecasting method from the [StatsForecast](../../../statsforecast/index.html) package, for which we reconcile the forecasts using [HierarchicalForecast](../../../hierarchicalforecast/index.html)."
    ]
   },
   {
diff --git a/nbs/docs/use-cases/electricity_peak_forecasting.ipynb b/nbs/docs/use-cases/electricity_peak_forecasting.ipynb
@@ -68,7 +68,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We assume you have NeuralForecast already installed. Check this guide for instructions on [how to install NeuralForecast](../getting-started/04_installation.ipynb).\n",
+    "We assume you have NeuralForecast already installed. Check this guide for instructions on [how to install NeuralForecast](../getting-started/installation.html).\n",
     "\n",
     "Install the necessary packages using `pip install neuralforecast`"
    ]
@@ -208,7 +208,7 @@
    "source": [
     "We fit the model by instantiating a `NeuralForecast` object with the following required parameters:\n",
     "\n",
-    "* `models`: a list of models. Select the models you want from [models](../capabilities/01_overview.ipynb) and import them.\n",
+    "* `models`: a list of models. Select the models you want from [models]( ../capabilities/overview.html.ipynb) and import them.\n",
     "\n",
     "* `freq`: a string indicating the frequency of the data. (See [panda's available frequencies](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases).)"
    ]
diff --git a/neuralforecast/common/_base_auto.py b/neuralforecast/common/_base_auto.py
@@ -376,7 +376,7 @@ def fit(
         the validation set that sequentially precedes the test set.
 
         Args:
-            dataset (NeuralForecast's `TimeSeriesDataset`): NeuralForecast's `TimeSeriesDataset` see details [here](./tsdataset)
+            dataset (NeuralForecast's `TimeSeriesDataset`): NeuralForecast's `TimeSeriesDataset` see details [here](./tsdataset.html)
             val_size (int): Size of temporal validation set (needs to be bigger than 0).
             test_size (int): Size of temporal test set (default 0).
             random_seed (int): Random seed for hyperparameter exploration algorithms, not yet implemented.
@@ -443,7 +443,7 @@ def predict(self, dataset, step_size=1, h=None, **data_kwargs):
         Predictions of the best performing model on validation.
 
         Args:
-            dataset (NeuralForecast's `TimeSeriesDataset`): NeuralForecast's `TimeSeriesDataset` see details [here](./tsdataset)
+            dataset (NeuralForecast's `TimeSeriesDataset`): NeuralForecast's `TimeSeriesDataset` see details [here](./tsdataset.html)
             step_size (int): Steps between sequential predictions, (default 1).
             h (int): Prediction horizon, if None, uses the model's fitted horizon. Defaults to None.
             **data_kwarg: Additional parameters for the dataset module.
diff --git a/neuralforecast/common/_base_model.py b/neuralforecast/common/_base_model.py
@@ -1940,7 +1940,7 @@ def fit(
         disk memory, to get them change `enable_checkpointing=True` in `__init__`.
 
         Args:
-            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset).
+            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset.html).
             val_size (int): Validation size for temporal cross-validation.
             random_seed (int): Random seed for pytorch initializer and numpy generators, overwrites model.__init__'s.
             test_size (int): Test size for temporal cross-validation.
@@ -1974,7 +1974,7 @@ def predict(
         Neural network prediction with PL's `Trainer` execution of `predict_step`.
 
         Args:
-            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset).
+            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation](./tsdataset.html).
             test_size (int): Test size for temporal cross-validation.
             step_size (int): Step size between each window.
             random_seed (int): Random seed for pytorch initializer and numpy generators, overwrites model.__init__'s.
@@ -2247,7 +2247,7 @@ def decompose(
         Available methods are `ESRNN`, `NHITS`, `NBEATS`, and `NBEATSx`.
 
         Args:
-            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation here](./tsdataset).
+            dataset (TimeSeriesDataset): NeuralForecast's `TimeSeriesDataset`, see [documentation here](./tsdataset.html).
             step_size (int): Step size between each window of temporal data.
             random_seed (int): Random seed for pytorch initializer and numpy generators, overwrites model.__init__'s.
             quantiles (list): Target quantiles to predict.
diff --git a/neuralforecast/models/hint.py b/neuralforecast/models/hint.py

Original file line number	Diff line number	Diff line change
`@@ -41,7 +41,7 @@`
`41`	`41`	`"metadata": {},`
`42`	`42`	`"source": [`
`43`	`43`	`":::{.callout-important}\n",`
`44`		`- "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/02_quickstart.ipynb) guide.\n",`
	`44`	`+ "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/quickstart.html) guide.\n",`
`45`	`45`	`":::"`
`46`	`46`	`]`
`47`	`47`	`},`
Original file line number	Diff line number	Diff line change
`@@ -26,7 +26,7 @@`
`26`	`26`	`"metadata": {},`
`27`	`27`	`"source": [`
`28`	`28`	`":::{.callout-important}\n",`
`29`		`- "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/02_quickstart.ipynb) guide.\n",`
	`29`	`+ "This Guide assumes basic knowledge on the NeuralForecast library. For a minimal example visit the [Getting Started](../getting-started/quickstart.html) guide.\n",`
`30`	`30`	`":::"`
`31`	`31`	`]`
`32`	`32`	`},`
Original file line number	Diff line number	Diff line change
`@@ -37,7 +37,7 @@`
`37`	`37`	`"* Train and Evaluation Losses Scale-dependent, percentage and scale independent errors, and parametric likelihoods.\n",`
`38`	`38`	`"* Automatic Model Selection Parallelized automatic hyperparameter tuning, that efficiently searches best validation configuration.\n",`
`39`	`39`	"* Simple Interface Unified SKLearn Interface for `StatsForecast` and `MLForecast` compatibility.\n",
`40`		- "* Model Collection: Out of the box implementation of `MLP`, `LSTM`, `RNN`, `TCN`, `DilatedRNN`, `NBEATS`, `NHITS`, `ESRNN`, `Informer`, `TFT`, `PatchTST`, `VanillaTransformer`, `StemGNN` and `HINT`. See the entire [collection here](../capabilities/01_overview)."
	`40`	+ "* Model Collection: Out of the box implementation of `MLP`, `LSTM`, `RNN`, `TCN`, `DilatedRNN`, `NBEATS`, `NHITS`, `ESRNN`, `Informer`, `TFT`, `PatchTST`, `VanillaTransformer`, `StemGNN` and `HINT`. See the entire [collection here](../capabilities/overview.html)."
`41`	`41`	`]`
`42`	`42`	`},`
`43`	`43`	`{`
Original file line number	Diff line number	Diff line change
`@@ -14,7 +14,7 @@`
`14`	`14`	`"cell_type": "markdown",`
`15`	`15`	`"metadata": {},`
`16`	`16`	`"source": [`
`17`		- "This notebook provides an example on how to start using the main functionalities of the NeuralForecast library. The `NeuralForecast` class allows users to easily interact with `NeuralForecast.models` PyTorch models. In this example we will forecast AirPassengers data with a classic `LSTM` and the recent `NHITS` models. The full list of available models is available [here](../capabilities/01_overview).\n"
	`17`	+ "This notebook provides an example on how to start using the main functionalities of the NeuralForecast library. The `NeuralForecast` class allows users to easily interact with `NeuralForecast.models` PyTorch models. In this example we will forecast AirPassengers data with a classic `LSTM` and the recent `NHITS` models. The full list of available models is available [here]( ../capabilities/overview.html).\n"
`18`	`18`	`]`
`19`	`19`	`},`
`20`	`20`	`{`
`@@ -412,7 +412,7 @@`
`412`	`412`	`"metadata": {},`
`413`	`413`	`"source": [`
`414`	`414`	`":::{.callout-tip}\n",`
`415`		- "For this guide we are using a simple `LSTM` model. More recent models, such as `TSMixer`, `TFT` and `NHITS` achieve better accuracy than `LSTM` in most settings. The full list of available models is available [here](../capabilities/01_overview).\n",
	`415`	+ "For this guide we are using a simple `LSTM` model. More recent models, such as `TSMixer`, `TFT` and `NHITS` achieve better accuracy than `LSTM` in most settings. The full list of available models is available [here]( ../capabilities/overview.html).\n",
`416`	`416`	`":::"`
`417`	`417`	`]`
`418`	`418`	`},`
Original file line number	Diff line number	Diff line change
`@@ -538,7 +538,7 @@`
`538`	`538`	`"\n",`
`539`	`539`	`"In Challu et al [2] we demonstrate that the N-HiTS model outperforms the latest transformers by more than 20% with 50 times less computation.\n",`
`540`	`540`	`"\n",`
`541`		`- "Learn how to use the N-HiTS and the NeuralForecast library in [this tutorial](../use-cases/electricity_peak_forecasting)."`
	`541`	`+ "Learn how to use the N-HiTS and the NeuralForecast library in [this tutorial](../use-cases/electricity_peak_forecasting.html)."`
`542`	`542`	`]`
`543`	`543`	`},`
`544`	`544`	`{`