Add some metadata to the model card

Hello!

## Preface
Nice work here! I'm excited to see models of this size for RAG. I'm going to dive more into your official library next.

## Pull Request overview
* Add `transformers` tag
* Add `text-generation` pipeline tag

## Details
These should make it a tad easier to find this model.

Also, as a heads up, in my experience, a small snippet in the model card with usage is often recommended to get people a good feel of what your model does, e.g.:
```python
rag = RAGWithCitations("PleIAs/Pleias-RAG-350M")

# Define query and sources
query = "What is the capital of France?"
sources = [
{
"text": "Paris is the capital and most populous city of France.",
"metadata": {"source": "Geographic Encyclopedia", "reliability": "high"}
},
{
"text": "The Eiffel Tower is located in Paris, France.",
"metadata": {"source": "Travel Guide", "year": 2020}
}
]

# Generate a response
response = rag.generate(query, sources)

# Print the final answer with citations
print(response["processed"]["clean_answer"])
```

(Except also include the import & printed output)

- Tom Aarsen

README.md

@@ -8,6 +8,9 @@ language:
 - es
 base_model:
 - PleIAs/Pleias-350m-Preview
+pipeline_tag: text-generation
+tags:
+- transformers
 ---
 
 
@@ -91,4 +94,4 @@ With only 350 million parameters, Pleias-RAG-350M is classified among the *phone
 
 We also release an unquantized [GGUF version](https://huggingface.co/PleIAs/Pleias-RAG-350M-gguf) for deployment on CPU. Our internal performance benchmarks suggest that waiting times are currently acceptable for most either even under constrained RAM: about 20 seconds for a complex generation including reasoning traces on 8g RAM and below. Since the model is unquantized, quality of text generation should be identical to the original model.
 
-Once integrated into a RAG system, Pleias-RAG-350M can also be use in a broader range of non-conversational use cases including user support or educational assistance. Through this release, we aims to make tiny model workable in production by relying systematically on an externalized memory.
+Once integrated into a RAG system, Pleias-RAG-350M can also be use in a broader range of non-conversational use cases including user support or educational assistance. Through this release, we aims to make tiny model workable in production by relying systematically on an externalized memory.