`nemo_microservices.types.shared_params.model_spec`#

Module Contents#

class nemo_microservices.types.shared_params.model_spec.ModelSpec#

Bases: typing_extensions.TypedDict

context_size: typing_extensions.Required[int]#

None

The maximum number of tokens to process together in a single forward pass through the model.

is_chat: typing_extensions.Required[bool]#

None

Indicates if the model is designed for multi-turn conversation rather than single-prompt completion.

num_parameters: typing_extensions.Required[int]#

None

The total number of trainable parameters in the model’s neural network architecture.

num_virtual_tokens: typing_extensions.Required[int]#

None

The number of virtual tokens the model can support for techniques such as prompt tuning, where special trainable embeddings are prepended to inputs.