BloomBackbone
classkeras_hub.models.BloomBackbone(
vocabulary_size,
num_layers,
num_heads,
hidden_dim,
intermediate_dim,
dropout=0.0,
layer_norm_epsilon=1e-05,
dtype=None,
**kwargs
)
A BLOOM decoder network.
This network implements a Transformer-based decoder network, BigScience Language Open-science Open-access Multilingual (BLOOM), as descriped in "BLOOM: A 176B-Parameter Open-Access Multilingual Language Model".
The default constructor gives a fully customizable, randomly initialized
Bloom model with any number of layers, heads, and embedding dimensions. To
load preset architectures and weights, use the from_preset()
constructor.
Disclaimer: Pre-trained models are provided on an "as is" basis, without warranties or conditions of any kind. The underlying model is provided by a third party and subject to a separate license, available here.
Arguments
keras.mixed_precision.DTypePolicy
. The dtype to use
for model computations and weights. Note that some computations,
such as softmax and layer normalization, will always be done at
float32 precision regardless of dtype.Example
input_data = {
"token_ids": np.ones(shape=(1, 12), dtype="int32"),
"padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]]),
}
# Pretrained BLOOM decoder.
model = keras_hub.models.BloomBackbone.from_preset("bloom_560m_multi")
model(input_data)
# Randomly initialized BLOOM decoder with a custom config.
model = keras_hub.models.BloomBackbone(
vocabulary_size=10,
num_layers=2,
num_heads=2,
hidden_dim=32,
intermediate_dim=32*4,
dropout=0.0,
layer_norm_epsilon=1e-5,
)
model(input_data)
from_preset
methodBloomBackbone.from_preset(preset, load_weights=True, **kwargs)
Instantiate a keras_hub.models.Backbone
from a model preset.
A preset is a directory of configs, weights and other file assets used
to save and load a pre-trained model. The preset
can be passed as a
one of:
'bert_base_en'
'kaggle://user/bert/keras/bert_base_en'
'hf://user/bert_base_en'
'./bert_base_en'
This constructor can be called in one of two ways. Either from the base
class like keras_hub.models.Backbone.from_preset()
, or from
a model class like keras_hub.models.GemmaBackbone.from_preset()
.
If calling from the base class, the subclass of the returning object
will be inferred from the config in the preset directory.
For any Backbone
subclass, you can run cls.presets.keys()
to list
all built-in presets available on the class.
Arguments
True
, the weights will be loaded into the
model architecture. If False
, the weights will be randomly
initialized.Examples
# Load a Gemma backbone with pre-trained weights.
model = keras_hub.models.Backbone.from_preset(
"gemma_2b_en",
)
# Load a Bert backbone with a pre-trained config and random weights.
model = keras_hub.models.Backbone.from_preset(
"bert_base_en",
load_weights=False,
)
Preset name | Parameters | Description |
---|---|---|
bloom_560m_multi | 559.21M | 24-layer Bloom model with hidden dimension of 1024. trained on 45 natural languages and 12 programming languages. |
bloom_1.1b_multi | 1.07B | 24-layer Bloom model with hidden dimension of 1536. trained on 45 natural languages and 12 programming languages. |
bloom_1.7b_multi | 1.72B | 24-layer Bloom model with hidden dimension of 2048. trained on 45 natural languages and 12 programming languages. |
bloom_3b_multi | 3.00B | 30-layer Bloom model with hidden dimension of 2560. trained on 45 natural languages and 12 programming languages. |
bloomz_560m_multi | 559.21M | 24-layer Bloom model with hidden dimension of 1024. finetuned on crosslingual task mixture (xP3) dataset. |
bloomz_1.1b_multi | 1.07B | 24-layer Bloom model with hidden dimension of 1536. finetuned on crosslingual task mixture (xP3) dataset. |
bloomz_1.7b_multi | 1.72B | 24-layer Bloom model with hidden dimension of 2048. finetuned on crosslingual task mixture (xP3) dataset. |
bloomz_3b_multi | 3.00B | 30-layer Bloom model with hidden dimension of 2560. finetuned on crosslingual task mixture (xP3) dataset. |
token_embedding
propertykeras_hub.models.BloomBackbone.token_embedding
A keras.layers.Embedding
instance for embedding token ids.
This layer embeds integer token ids to the hidden dim of the model.
enable_lora
methodBloomBackbone.enable_lora(rank)
Enable Lora on the backbone.
Calling this method will freeze all weights on the backbone,
while enabling Lora on the query & value EinsumDense
layers
of the attention layers.