> ## Documentation Index
> Fetch the complete documentation index at: https://baseten-philip-copy-0226.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started

> Building your first Truss

<Card title="View on Github" icon="github" href="https://github.com/basetenlabs/truss-examples/tree/main/01-getting-started-bert" />

In this example, we go through building your first Truss model. We'll be using the HuggingFace transformers
library to build a text classification model that can detect sentiment of text.

# Step 1: Implementing the model

Set up imports for this model. In this example, we simply use the HuggingFace transformers library.

```python model/model.py
from transformers import pipeline


```

Every Truss model must implement a `Model` class. This class must have:

* an `__init__` function
* a `load` function
* a `predict` function

In the `__init__` function, set up any variables that will be used in the `load` and `predict` functions.

```python model/model.py
class Model:
    def __init__(self, **kwargs):
        self._model = None

```

In the `load` function of the Truss, we implement logic
involved in downloading the model and loading it into memory.
For this Truss example, we define a HuggingFace pipeline, and choose
the `text-classification` task, which uses BERT for text classification under the hood.

Note that the load function runs once when the model starts.

```python model/model.py
    def load(self):
        self._model = pipeline("text-classification")

```

In the `predict` function of the Truss, we implement logic related
to actual inference. For this example,  we just call the HuggingFace pipeline
that we set up in the `load` function.

```python model/model.py
    def predict(self, model_input):
        return self._model(model_input)
```

# Step 2: Writing the config.yaml

Each Truss has a config.yaml file where we can configure
options related to the deployment. It's in this file where
we can define requirements, resources, and runtime options like
secrets and environment variables

### Basic Options

In this section, we can define basic metadata about the model,
such as the name, and the Python version to build with.

```yaml config.yaml
model_name: bert
python_version: py310
model_metadata:
  example_model_input: { "text": "Hello my name is {MASK}" }


```

### Set up python requirements

In this section, we define any pip requirements that
we need to run the model. To run this, we need PyTorch
and Tranformers.

```yaml config.yaml
requirements:
  - torch==2.0.1
  - transformers==4.33.2

```

### Configure the resources needed

In this section, we can configure resources
needed to deploy this model. Here, we have no need for a GPU
so we leave the accelerator section blank.

```yaml config.yaml
resources:
  accelerator: null
  cpu: '1'
  memory: 2Gi
  use_gpu: false

```

### Other config options

Truss also has provisions for adding other runtime options
packages. In this example, we don't need these, so we leave
this empty for now.

```yaml config.yaml
secrets: {}
system_packages: []
environment_variables: {}
external_package_dirs: []

```

# Step 3: Deploying & running inference

Deploy the model with the following command:

```bash
$ truss push
```

And then you can performance inference with:

```
$ truss predict -d '"Truss is awesome!"'
```

<RequestExample>
  ```python model/model.py
  from transformers import pipeline


  class Model:
      def __init__(self, **kwargs):
          self._model = None

      def load(self):
          self._model = pipeline("text-classification")

      def predict(self, model_input):
          return self._model(model_input)
  ```

  ```yaml config.yaml
  model_name: bert
  python_version: py310
  model_metadata:
    example_model_input: { "text": "Hello my name is {MASK}" }


  requirements:
    - torch==2.0.1
    - transformers==4.33.2

  resources:
    accelerator: null
    cpu: '1'
    memory: 2Gi
    use_gpu: false

  secrets: {}
  system_packages: []
  environment_variables: {}
  external_package_dirs: []

  ```
</RequestExample>