Merge `transformers` vision models with text-2-text models

Co-authored-by: Robin Picard <robin@dottxt.co>

This PR turn the class `TransformersVision` into
`TransformersMultiModal` that accommodates both vision and audio models.
We should be able to use this same class for video models with minimal
change, but I did not find a good model to test it out.

Modify the `VLLM` class to inherit from the base `Model` class and
implement the standard interface of models for the v1.0.
This PR also creates tests for the `VLLM` model in the `tests/models`
directory and remove the previous tests for it in `tests/generate`.

We are currently using intermediate `Json`, `Choice` and `List` classes
which, in addition to being cumbersome, are not useful abstractions.
This commit bypasses these abstractions to handle the output types
directly at the level of `GeminiTypeAdapter`.

…and Batching examples

…string errors

…sformers multimodal type adapter

…t errors

…ssets and the mm chat template format

…ing asset and type keys

…cenario, and added Audio and Video tests