ModelTRTQuantizationConfiguration¶
- class baseten.client.modelconfig.ModelTRTQuantizationConfiguration(*, calib_size=1024, calib_dataset='abisee/cnn_dailymail', calib_max_seq_length=1536, **extra_data)¶
Bases:
BaseModel- Parameters:
- model_config = {'extra': 'allow'}¶
Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].