Gemma3CausalLM
classkeras_hub.models.Gemma3CausalLM(preprocessor, backbone, **kwargs)
An end-to-end multimodal Gemma3 model for causal language modeling.
A causal language model (LM) predicts the next token based on previous tokens. This task setup can be used to train the model unsupervised on images and plain text inputs, or to autoregressively generate plain text similar to the data used for training. Note that the model is image-text in, text out.
This model has a generate()
method, which generates text based on a
prompt. The generation strategy used is controlled by an additional
sampler
argument on compile()
. You can recompile the model with
different keras_hub.samplers
objects to control the generation. By
default, "greedy"
sampling will be used.
This model can optionally be configured with a preprocessor
layer, in
which case it will automatically apply preprocessing to string inputs during
fit()
, predict()
, evaluate()
and generate()
. This is done by default
when creating the model with from_preset()
.
Arguments
keras_hub.models.Gemma3CausalLMPreprocessor
or
None
. If None
, this model will not apply preprocessing, and
inputs should be preprocessed before calling the model.keras_hub.models.Gemma3Backbone
instance.from_preset
methodGemma3CausalLM.from_preset(preset, load_weights=True, **kwargs)
Instantiate a keras_hub.models.Task
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
one of:
'bert_base_en'
'kaggle://user/bert/keras/bert_base_en'
'hf://user/bert_base_en'
'./bert_base_en'
For any Task
subclass, you can run cls.presets.keys()
to list all
built-in presets available on the class.
This constructor can be called in one of two ways. Either from a task
specific base class like keras_hub.models.CausalLM.from_preset()
, or
from a model class like
keras_hub.models.BertTextClassifier.from_preset()
.
If calling from the a base class, the subclass of the returning object
will be inferred from the config in the preset directory.
Arguments
True
, saved weights will be loaded into
the model architecture. If False
, all weights will be
randomly initialized.Examples
# Load a Gemma generative task.
causal_lm = keras_hub.models.CausalLM.from_preset(
"gemma_2b_en",
)
# Load a Bert classification task.
model = keras_hub.models.TextClassifier.from_preset(
"bert_base_en",
num_classes=2,
)
Preset | Parameters | Description |
---|---|---|
gemma3_1b | 999.89M | 1 billion parameter, 26-layer, text-only pretrained Gemma3 model. |
gemma3_instruct_1b | 999.89M | 1 billion parameter, 26-layer, text-only instruction-tuned Gemma3 model. |
gemma3_4b_text | 3.88B | 4 billion parameter, 34-layer, text-only pretrained Gemma3 model. |
gemma3_instruct_4b_text | 3.88B | 4 billion parameter, 34-layer, text-only instruction-tuned Gemma3 model. |
gemma3_4b | 4.30B | 4 billion parameter, 34-layer, vision+text pretrained Gemma3 model. |
gemma3_instruct_4b | 4.30B | 4 billion parameter, 34-layer, vision+text instruction-tuned Gemma3 model. |
gemma3_12b_text | 11.77B | 12 billion parameter, 48-layer, text-only pretrained Gemma3 model. |
gemma3_instruct_12b_text | 11.77B | 12 billion parameter, 48-layer, text-only instruction-tuned Gemma3 model. |
gemma3_12b | 12.19B | 12 billion parameter, 48-layer, vision+text pretrained Gemma3 model. |
gemma3_instruct_12b | 12.19B | 12 billion parameter, 48-layer, vision+text instruction-tuned Gemma3 model. |
gemma3_27b_text | 27.01B | 27 billion parameter, 62-layer, text-only pretrained Gemma3 model. |
gemma3_instruct_27b_text | 27.01B | 27 billion parameter, 62-layer, text-only instruction-tuned Gemma3 model. |
gemma3_27b | 27.43B | 27 billion parameter, 62-layer, vision+text pretrained Gemma3 model. |
gemma3_instruct_27b | 27.43B | 27 billion parameter, 62-layer, vision+text instruction-tuned Gemma3 model. |
generate
methodGemma3CausalLM.generate(
inputs, max_length=None, stop_token_ids="auto", strip_prompt=False
)
Generate text given prompt inputs
.
This method generates text based on given inputs
. The sampling method
used for generation can be set via the compile()
method.
If inputs
are a tf.data.Dataset
, outputs will be generated
"batch-by-batch" and concatenated. Otherwise, all inputs will be handled
as a single batch.
If a preprocessor
is attached to the model, inputs
will be
preprocessed inside the generate()
function and should match the
structure expected by the preprocessor
layer (usually raw strings).
If a preprocessor
is not attached, inputs should match the structure
expected by the backbone
. See the example usage above for a
demonstration of each.
Arguments
tf.data.Dataset
. If a
preprocessor
is attached to the model, inputs
should match
the structure expected by the preprocessor
layer. If a
preprocessor
is not attached, inputs
should match the
structure expected the backbone
model.sequence_length
of the
preprocessor
. If preprocessor
is None
, inputs
should be
should be padded to the desired maximum length and this argument
will be ignored.None
, "auto", or tuple of token ids.
Defaults to "auto" which uses the
preprocessor.tokenizer.end_token_id
. Not specifying a
processor will produce an error. None stops generation after
generating max_length
tokens. You may also specify a list of
token id's the model should stop on. Note that sequences of
tokens will each be interpreted as a stop token, multi-token
stop sequences are not supported.backbone
propertykeras_hub.models.Gemma3CausalLM.backbone
A keras_hub.models.Backbone
model with the core architecture.
preprocessor
propertykeras_hub.models.Gemma3CausalLM.preprocessor
A keras_hub.models.Preprocessor
layer used to preprocess input.