Demo code from readme fails

[rain-1]

I get this error:

  File "/home/ubuntu/code/Orpheus-TTS/./a.py", line 5, in <module>
    model = OrpheusModel(model_name ="canopylabs/orpheus-tts-0.1-finetune-prod", max_model_len=2048)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: OrpheusModel.__init__() got an unexpected keyword argument 'max_model_len'

deleting , max_model_len=2048 allowed the code to progress.

but then I got this crash:

[rank0]: Traceback (most recent call last):
[rank0]:   File "/home/ubuntu/code/Orpheus-TTS/./a.py", line 5, in <module>
[rank0]:     model = OrpheusModel(model_name ="canopylabs/orpheus-tts-0.1-finetune-prod")
[rank0]:             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...
[rank0]: ValueError: The model's max seq len (131072) is larger than the maximum number of tokens that can be stored in KV cache (62896). Try increasing `gpu_memory_utilization` or decreasing `max_model_len` when initializing the engine.

[rain-1]

I stopped the crashing by putting this, but this isn't a complete solution.

    def _setup_engine(self):
        engine_args = AsyncEngineArgs(
            model=self.model_name,
            dtype=self.dtype,
            max_model_len=2048
        )