[FeatureRequest] Constraint input & output sizes no matter the dataset

[markVaykhansky]

Description
Currently the user can limit the prompt input size and model output size only when using emulated data type.
Please separate the input & output sizes configuration from the type of the data.

Suggested Implementation
Add --data-max-input-tokens and --max-output-tokens parameters to the CLI.
If the data-type is file or transformers and the input size is larger than data_max_input_tokens it should cut-off the input at the limit.

[rgreenberg1]

@markVaykhansky just following up here. How does the following proposal work?

If we need to limit the output tokens, pre-process the dataset. For input tokens, we have an environment variable GUIDELLM__OPENAI__MAX_OUTPUT_TOKENS

cc @markurtz @sjmonson

[markurtz]

Closing this out since this was addressed in #162