Estimate effect for multiple categorical treatments using DML

[matsuobasho]

Is it possible to estimate the effect of a DAG with multiple treatments using DML? I read the multiple treatments tutorial, but this has continuous treatment variables and was using linear regression for the t modeling.
Currently getting error on the below:

confounders = [
    'Size', 'Employee Count', 'PC Count', 'IT Spend', 'Major Flag',
    'Global Flag', 'Commercial Flag', 'SMC Flag'
]

model = CausalModel(
    data=df,
    treatment=['Discount', 'Tech Support'],
    outcome='Revenue',
    common_causes=
    confounders
)

tree_model = DecisionTreeClassifier(max_depth=5)

causal_estimate_reg = model.estimate_effect(
    identified_estimand=identified_estimand,
    method_name="backdoor.econml.dml.LinearDML",
    control_value = (0,0),
    treatment_value=(1,1),
    target_units="ate",
    method_params=  {'init_params': {'model_y': GradientBoostingRegressor(),
                                   'model_t': tree_model,
                                   'discrete_treatment': True},
                    'fit_params': {}
                    }
           )

Error:
ValueError: Found input variables with inconsistent numbers of samples: [2000, 4000]