[HWORKS-1224] Add vLLM to docs and update outdated descriptions and images

Author: javierdlrm

docs/assets/images/guides/mlops/serving/deployment_adv_form_batcher.png

@@ -0,0 +1,62 @@
+# How To Export a LLM Model
+
+## Introduction
+
+In this guide you will learn how to export a [Large Language Model (LLM)](https://www.hopsworks.ai/dictionary/llms-large-language-models) and register it in the Model Registry.
+
+## Code
+
+### Step 1: Connect to Hopsworks
+
+=== "Python"
+    ```python
+    import hopsworks
+
+    project = hopsworks.login()
+
+    # get Hopsworks Model Registry handle
+    mr = project.get_model_registry()
+    ```
+
+### Step 2: Download the LLM
+
+Download your base or fine-tuned LLM. LLMs can typically be downloaded using the official frameworks provided by their creators (e.g., HuggingFace, Ollama, ...)
+
+=== "Python"
+    ```python
+    # Download LLM (e.g., using huggingface to download Llama-3.1-8B base model)
+    from huggingface_hub import snapshot_download
+
+    model_dir = snapshot_download(
+                    "meta-llama/Llama-3.1-8B",
+                    ignore_patterns="original/*"
+                )
+    ```
+
+### Step 3: (Optional) Fine-tune LLM
+
+If necessary, fine-tune your LLM with an [instruction set](https://www.hopsworks.ai/dictionary/instruction-datasets-for-fine-tuning-llms). A LLM can be fine-tuned fully or using [Parameter Efficient Fine Tuning (PEFT)](https://www.hopsworks.ai/dictionary/parameter-efficient-fine-tuning-of-llms) methods such as LoRA or QLoRA.
+
+=== "Python"
+    ```python
+    # Fine-tune LLM using PEFT (LoRA, QLoRA) or other methods
+    model_dir = ...
+    ```
+
+### Step 4: Register model in registry
+
+Use the `ModelRegistry.llm.create_model(..)` function to register a model as LLM. Define a name, and attach optional metrics for your model, then invoke the `save()` function with the parameter being the path to the local directory where the model was exported to.
+
+=== "Python"
+    ```python
+    # Model evaluation metrics
+    metrics = {'f1-score': 0.8, 'perplexity': 31.62, 'bleu-score': 0.73}
+
+    llm_model = mr.llm.create_model("llm_model", metrics=metrics)
+
+    llm_model.save(model_dir)
+    ```
+
+## Going Further
+
+You can attach an [Input Example](../input_example.md) and a [Model Schema](../input_example.md) to your model to document the shape and type of the data the model was trained on.

docs/assets/images/guides/mlops/serving/deployment_adv_form_kserve.png

@@ -8,54 +8,53 @@ In this guide you will learn how to export a generic Python model and register i
 
 ### Step 1: Connect to Hopsworks
 
-```python
-import hopsworks
+=== "Python"
+    ```python
+    import hopsworks
 
-project = hopsworks.login()
+    project = hopsworks.login()
 
-# get Hopsworks Model Registry handle
-mr = project.get_model_registry()
-```
+    # get Hopsworks Model Registry handle
+    mr = project.get_model_registry()
+    ```
 
 ### Step 2: Train
 
 Define your XGBoost model and run the training loop.
 
-```python
-# Define a model
-model = XGBClassifier()
+=== "Python"
+    ```python
+    # Define a model
+    model = XGBClassifier()
 
-# Train model
-model.fit(X_train, y_train)
-
-```
+    # Train model
+    model.fit(X_train, y_train)
+    ```
 
 ### Step 3: Export to local path
 
 Export the XGBoost model to a directory on the local filesystem.
 
-```python
-
-model_file = "model.json"
-
-model.save_model(model_file)
+=== "Python"
+    ```python
+    model_file = "model.json"
 
-```
+    model.save_model(model_file)
+    ```
 
 ### Step 4: Register model in registry
 
 Use the `ModelRegistry.python.create_model(..)` function to register a model as a Python model. Define a name, and attach optional metrics for your model, then invoke the `save()` function with the parameter being the path to the local directory where the model was exported to.
 
-```python
-
-# Model evaluation metrics
-metrics = {'accuracy': 0.92}
-
-py_model = mr.python.create_model("py_model", metrics=metrics)
+=== "Python"
+    ```python
+    # Model evaluation metrics
+    metrics = {'accuracy': 0.92}
 
-py_model.save(model_dir)
+    py_model = mr.python.create_model("py_model", metrics=metrics)
 
-```
+    py_model.save(model_dir)
+    ```
 
 ## Going Further
 

docs/assets/images/guides/mlops/serving/deployment_adv_form_logger.png

@@ -8,53 +8,52 @@ In this guide you will learn how to export a Scikit-learn model and register it
 
 ### Step 1: Connect to Hopsworks
 
-```python
-import hopsworks
+=== "Python"
+    ```python
+    import hopsworks
 
-project = hopsworks.login()
+    project = hopsworks.login()
 
-# get Hopsworks Model Registry handle
-mr = project.get_model_registry()
-```
+    # get Hopsworks Model Registry handle
+    mr = project.get_model_registry()
+    ```
 
 ### Step 2: Train
 
 Define your Scikit-learn model and run the training loop.
 
-```python
-# Define a model
-iris_knn = KNeighborsClassifier(..)
+=== "Python"
+    ```python
+    # Define a model
+    iris_knn = KNeighborsClassifier(..)
 
-iris_knn.fit(..)
-
-```
+    iris_knn.fit(..)
+    ```
 
 ### Step 3: Export to local path
 
 Export the Scikit-learn model to a directory on the local filesystem.
 
-```python
-
-model_file = "skl_knn.pkl"
-
-joblib.dump(iris_knn, model_file)
+=== "Python"
+    ```python
+    model_file = "skl_knn.pkl"
 
-```
+    joblib.dump(iris_knn, model_file)
+    ```
 
 ### Step 4: Register model in registry
 
 Use the `ModelRegistry.sklearn.create_model(..)` function to register a model as a Scikit-learn model. Define a name, and attach optional metrics for your model, then invoke the `save()` function with the parameter being the path to the local directory where the model was exported to.
 
-```python
-
-# Model evaluation metrics
-metrics = {'accuracy': 0.92}
-
-skl_model = mr.sklearn.create_model("skl_model", metrics=metrics)
+=== "Python"
+    ```python
+    # Model evaluation metrics
+    metrics = {'accuracy': 0.92}
 
-skl_model.save(model_file)
+    skl_model = mr.sklearn.create_model("skl_model", metrics=metrics)
 
-```
+    skl_model.save(model_file)
+    ```
 
 ## Going Further
 

docs/assets/images/guides/mlops/serving/deployment_adv_form_trans.png

@@ -12,60 +12,59 @@ In this guide you will learn how to export a TensorFlow model and register it in
 
 ### Step 1: Connect to Hopsworks
 
-```python
-import hopsworks
+=== "Python"
+    ```python
+    import hopsworks
 
-project = hopsworks.login()
+    project = hopsworks.login()
 
-# get Hopsworks Model Registry handle
-mr = project.get_model_registry()
-```
+    # get Hopsworks Model Registry handle
+    mr = project.get_model_registry()
+    ```
 
 ### Step 2: Train
 
 Define your TensorFlow model and run the training loop.
 
-```python
-# Define a model
-model = tf.keras.Sequential()
+=== "Python"
+    ```python
+    # Define a model
+    model = tf.keras.Sequential()
 
-# Add layers
-model.add(..)
+    # Add layers
+    model.add(..)
 
-# Compile the model.
-model.compile(..)
-    
-# Train the model
-model.fit(..)
-
-```
+    # Compile the model.
+    model.compile(..)
+        
+    # Train the model
+    model.fit(..)
+    ```
 
 ### Step 3: Export to local path
 
 Export the TensorFlow model to a directory on the local filesystem.
 
-```python
-
-model_dir = "./model"
-
-tf.saved_model.save(model, model_dir)
+=== "Python"
+    ```python
+    model_dir = "./model"
 
-```
+    tf.saved_model.save(model, model_dir)
+    ```
 
 ### Step 4: Register model in registry
 
 Use the `ModelRegistry.tensorflow.create_model(..)` function to register a model as a TensorFlow model. Define a name, and attach optional metrics for your model, then invoke the `save()` function with the parameter being the path to the local directory where the model was exported to.  
 
-```python
-
-# Model evaluation metrics
-metrics = {'accuracy': 0.92}
-
-tf_model = mr.tensorflow.create_model("tf_model", metrics=metrics)
+=== "Python"
+    ```python
+    # Model evaluation metrics
+    metrics = {'accuracy': 0.92}
 
-tf_model.save(model_dir)
+    tf_model = mr.tensorflow.create_model("tf_model", metrics=metrics)
 
-```
+    tf_model.save(model_dir)
+    ```
 
 ## Going Further
 

docs/assets/images/guides/mlops/serving/deployment_creating.png

@@ -1,6 +1,6 @@
 # Model Registry Guides
 
-Hopsworks Model Registry is a centralized repository, within an organization, to manage machine learning models. A model is the product of training a machine learning algorithm with training data.
+**Hopsworks Model Registry** is a centralized repository, within an organization, to manage machine learning models. A model is the product of training a machine learning algorithm with training data.
 
 This section provides guides for creating models and publish them to the Model Registry to make them available for download for batch predictions, or deployed to serve realtime applications.
 
@@ -13,6 +13,8 @@ Follow these framework-specific guides to export a Model to the Model Registry.
 
 * [Scikit-learn](frameworks/skl.md)
 
+* [LLM](frameworks/llm.md)
+
 * [Other frameworks](frameworks/python.md)
 
 

docs/assets/images/guides/mlops/serving/deployment_grpc_select.png

@@ -12,33 +12,34 @@ In this guide you will learn how to attach an input example to a model. An input
 
 ### Step 1: Connect to Hopsworks
 
-```python
-import hopsworks
+=== "Python"
+    ```python
+    import hopsworks
 
-project = hopsworks.login()
+    project = hopsworks.login()
 
-# get Hopsworks Model Registry handle
-mr = project.get_model_registry()
-```
+    # get Hopsworks Model Registry handle
+    mr = project.get_model_registry()
+    ```
 
 ### Step 2: Generate an input example
 
 Generate an input example which corresponds to a valid input to your model. Currently we support `pandas.DataFrame, pandas.Series, numpy.ndarray, list` to be passed as input example.
 
-```python
-import numpy as np
+=== "Python"
+    ```python
+    import numpy as np
 
-input_example = np.random.randint(0, high=256, size=784, dtype=np.uint8)
-
-```
+    input_example = np.random.randint(0, high=256, size=784, dtype=np.uint8)
+    ```
 
 ### Step 3: Set input_example parameter
 
 Set the `input_example` parameter in the `create_model` function and call `save()` to attaching it to the model and register it in the registry.
-```python
-
-model = mr.tensorflow.create_model(name="mnist",
-                                   input_example=input_example)
-model.save("./model")
 
-```
+=== "Python"
+    ```python
+    model = mr.tensorflow.create_model(name="mnist",
+                                    input_example=input_example)
+    model.save("./model")
+    ```