easydel.modules.exaone.modeling_exaone_flax

easydel.modules.exaone.modeling_exaone_flax#

class easydel.modules.exaone.modeling_exaone_flax.ExaoneAttention(*args: Any, **kwargs: Any)[source]#

Bases: Module

class easydel.modules.exaone.modeling_exaone_flax.ExaoneAttentionInner(*args: Any, **kwargs: Any)[source]#

Bases: AttentionModule

class easydel.modules.exaone.modeling_exaone_flax.ExaoneDecoderLayer(*args: Any, **kwargs: Any)[source]#

Bases: Module

class easydel.modules.exaone.modeling_exaone_flax.ExaoneForCausalLM(*args: Any, **kwargs: Any)[source]#

Bases: EasyDeLBaseModule

Exaone model with a language modeling head for causal language modeling tasks.

This model extends the base ExaoneModel by adding a linear language modeling head on top of the transformer model. It’s designed for generative tasks and can be used for text generation.

class easydel.modules.exaone.modeling_exaone_flax.ExaoneForSequenceClassification(*args: Any, **kwargs: Any)[source]#

Bases: EasyDeLBaseModule

class easydel.modules.exaone.modeling_exaone_flax.ExaoneGatedMLP(*args: Any, **kwargs: Any)[source]#

Bases: Module

class easydel.modules.exaone.modeling_exaone_flax.ExaoneModel(*args: Any, **kwargs: Any)[source]#

Bases: EasyDeLBaseModule

property frequencies#

Retrieves or computes the frequency components (e.g., for RoPE) from the configuration.

Uses self.config.get_basic_frequencies() and caches the result.

Returns

The frequency components, potentially cached.

Return type

jnp.ndarray

Contents