Keep the pipeline tag as Auto Detected.

Hey team!

The generated code snippet for the model creates an issue as suggested [here](https://github.com/huggingface/huggingface.js/issues/1803).

The issue is that the pipeline is tagged as `image-text-to-text`, which uses `AutoModelForImageTextToText`. The model does not support the API and only supports `AutoModel` (with remote code).

The easiest option to rectify the issue is to keep `pipeline_tag` as Auto-detected, which would in turn produce the following code snippet that works ⬇
```py
pipe = pipeline("feature-extraction", model="openbmb/MiniCPM-V-4_5", trust_remote_code=True)
```

The other option (a bit convoluted) is to write a custom pipeline.
The docs of adding a new pipeline is here: https://huggingface.co/docs/transformers/en/add_new_pipeline#adding-a-new-pipeline


Let me know what you think is best! 🤗

README.md

@@ -1,5 +1,4 @@
 ---
-pipeline_tag: image-text-to-text
 datasets:
 - openbmb/RLAIF-V-Dataset
 library_name: transformers