[sharktank] Remove redundant parallelism fields in LlamaModelConfig.to_properties

[sogartar]

We are already saving these in parallelism_config.

[Alex-Vasile]

tensor_parallelism_size is not being saved by parallelism_config

[sogartar]

But it is dynamically computed from there
LlamaModelConfig:

    @property
    def tensor_parallelism_size(self) -> int:
        return self.parallelism_config.tensor_parallelism_size

ParallelismConfig:

    @property
    def tensor_parallelism_size(self) -> int:
        """
        How many devices are involved for tensor parallel sharding.
        If greater than 1, the model will expect sharded model parameters and function
        arguments.
        """
        return len(self.devices_for_pipeline(0))

Actually until now this init.

return LlamaModelConfig(**kwargs)

Was causing an overwrite of the method-like properties.

    @property
    def pipeline_parallelism_size(self) -> int:
        return self.parallelism_config.pipeline_size

    @property
    def tensor_parallelism_size(self) -> int:
        return self.parallelism_config.tensor_parallelism_size

This may cause a discrepancy with LlamaModelConfig.parallelism_config.

One more casualty of the power of Python's dynamism.

[sogartar]

Nevermind, its not that.