[Feature Request]: Observation weights

### Describe the feature you want to propose or implement

Hi! I am working on using the DML package to try and reproduce previous impact evaluation studies done with OLS to study causal inference. I have a dataset that includes observation weights and I can't seem to find a way to implement this as a parameter when fitting the PLIV model. Resampling the dataset has not seemed to work as the weights are within quite an unconventional range, [0.000004,0.05], and it becomes difficult to expand the data and keep the runtime at reasonable level. I'm not sure if I am missing something in the package where I can include these features. Thank you for your time!

Best,

Kami

### Propose a possible solution or implementation

_No response_

### Did you consider alternatives to the proposed solution. If yes, please describe

_No response_

### Comments, context or references

_No response_

Start by locating the PLIV model fitting entry point in the DoubleML R package and checking how fitting parameters are passed. Review whether observation weights are supported anywhere in the package, then define completion as allowing weighted PLIV fitting without dataset expansion and covering the behavior with tests.

Written by the indexing model from the issue text.