<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/core/reversible_embedding.py#L16-L541) |

An embedding layer which can project backwards to the input dim.

Inherits From: [`Embedding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding), [`Layer`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer), [`Operation`](https://www.tensorflow.org/api_docs/python/tf/keras/Operation)

    tf.keras.layers.ReversibleEmbedding(
        input_dim,
        output_dim,
        tie_weights=True,
        embeddings_initializer='uniform',
        embeddings_regularizer=None,
        embeddings_constraint=None,
        mask_zero=False,
        reverse_dtype=None,
        logit_soft_cap=None,
        **kwargs
    )

This layer is an extension of [`keras.layers.Embedding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding) for language models.
This layer can be called "in reverse" with `reverse=True`, in which case the
layer will linearly project from `output_dim` back to `input_dim`.

By default, the reverse projection will use the transpose of the
`embeddings` weights to project to `input_dim` (weights are "tied"). If
`tie_weights=False`, the model will use a separate, trainable variable for
reverse projection.

This layer has no bias terms.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `input_dim` | Integer. Size of the vocabulary, i.e. maximum integer index + 1. |
| `output_dim` | Integer. Dimension of the dense embedding. |
| `tie_weights` | Boolean, whether or not the matrix for embedding and the matrix for the `reverse` projection should share the same weights. |
| `embeddings_initializer` | Initializer for the `embeddings` matrix (see [`keras.initializers`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers)). |
| `embeddings_regularizer` | Regularizer function applied to the `embeddings` matrix (see [`keras.regularizers`](https://www.tensorflow.org/api_docs/python/tf/keras/regularizers)). |
| `embeddings_constraint` | Constraint function applied to the `embeddings` matrix (see [`keras.constraints`](https://www.tensorflow.org/api_docs/python/tf/keras/constraints)). |
| `mask_zero` | Boolean, whether or not the input value 0 is a special "padding" value that should be masked out. |
| `reverse_dtype` | The dtype for the reverse projection computation. Defaults to the `compute_dtype` of the layer. |
| `logit_soft_cap` | If `logit_soft_cap` is set and `reverse=True`, the output logits will be scaled by `tanh(logits / logit_soft_cap) * logit_soft_cap`. This narrows the range of output logits and can improve training. |
| `**kwargs` | other keyword arguments passed to [`keras.layers.Embedding`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Embedding), including `name`, `trainable`, `dtype` etc. |

<br />

<br />

<br />

<br />

| ## Call arguments ||
|---|---|
| `inputs` | The tensor inputs to the layer. |
| `reverse` | Boolean. If `True` the layer will perform a linear projection from `output_dim` to `input_dim`, instead of a normal embedding call. Default to `False`. |

<br />

#### Example:

    batch_size = 16
    vocab_size = 100
    hidden_dim = 32
    seq_length = 50

    # Generate random inputs.
    token_ids = np.random.randint(vocab_size, size=(batch_size, seq_length))

    embedding = keras.layers.ReversibleEmbedding(vocab_size, hidden_dim)
    # Embed tokens to shape `(batch_size, seq_length, hidden_dim)`.
    hidden_states = embedding(token_ids)
    # Project hidden states to shape `(batch_size, seq_length, vocab_size)`.
    logits = embedding(hidden_states, reverse=True)

#### References:

- [Vaswani et al., 2017](https://arxiv.org/abs/1706.03762)
- [Press and Wolf, 2016](https://arxiv.org/abs/1608.05859)

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `embeddings` | <br /> <br /> |
| `input` | Retrieves the input tensor(s) of a symbolic operation. <br /> Only returns the tensor(s) corresponding to the *first time* the operation was called. |
| `output` | Retrieves the output tensor(s) of a layer. <br /> Only returns the tensor(s) corresponding to the *first time* the operation was called. |
| `variable_serialization_spec` | Returns a dict mapping quantization modes to variable names in order. <br /> This spec is used by `save_own_variables` and `load_own_variables` to determine the correct ordering of variables during serialization for each quantization mode. `None` means no quantization. |

<br />

## Methods

### `enable_lora`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/core/embedding.py#L214-L259)

    enable_lora(
        rank,
        lora_alpha=None,
        a_initializer='he_uniform',
        b_initializer='zeros'
    )

### `from_config`

[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/core/embedding.py#L369-L377)

    @classmethod
    from_config(
        config
    )

Creates an operation from its config.

This method is the reverse of `get_config`, capable of instantiating the
same operation from the config dictionary.

> [!NOTE]
> **Note:** If you override this method, you might receive a serialized dtype config, which is a `dict`. You can deserialize it as follows:

    if "dtype" in config and isinstance(config["dtype"], dict):
        policy = dtype_policies.deserialize(config["dtype"])

<br />

<br />

<br />

| Args ||
|---|---|
| `config` | A Python dictionary, typically the output of `get_config`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| An operation instance. ||

<br />