Improve model card: Add library name, pipeline tag and link to code (#2)

- Improve model card: Add library name, pipeline tag and link to code (78c9661e3a5b4c6796a7b433de3fee2b18343bb8)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,16 +1,17 @@
 ---
-license: apache-2.0
+base_model:
+- PleIAs/Pleias-1.2B-Preview
 language:
 - en
 - fr
 - it
 - de
 - es
-base_model:
-- PleIAs/Pleias-1.2B-Preview
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
-
 # Pleias-RAG-1B
 
 <div align="center">
@@ -62,7 +63,7 @@ The structured reasoning traces include the following steps:
 ### Multilinguality
 Pleias-RAG-1B is able to read and write in the main European languages: French, German, Italian, Spanish, Polish, Latin and Portuguese.
 
-To date, it is the only SLM with negligible loss of performance in leading European languages for RAG-related tasks. On a translated set of HotPotQA we observed a significant drop of performance in most SLMs from 10\% to 30-35\% for sub-1B models. 
+To date, it is the only SLM with negligible loss of performance in leading European languages for RAG-related tasks. On a translated set of HotPotQA we observed a significant drop of performance in most SLMs from 10% to 30-35% for sub-1B models. 
 
 <p align="center">
   <img width="80%" src="figures/language_benchmark.png">
@@ -88,6 +89,8 @@ The easiest way to deploy Pleias-RAG-1B is through [our official library](https:
 A typical minimal example:
 
 ```python
+from rag_library import RAGWithCitations
+
 rag = RAGWithCitations("PleIAs/Pleias-RAG-1B")
 
 # Define query and sources
@@ -122,4 +125,4 @@ With 1.2B parameters, Pleias-RAG-1B can be readily deployed in many constrained
 
 We also release an [unquantized GGUF version](https://huggingface.co/PleIAs/Pleias-RAG-1B-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-1B can also be used in a broader range of non-conversational use cases including user support or educational assistance. Through this release, we aims to make SLMs workable in production by relying systematically on an externalized memory.
+Once integrated into a RAG system, Pleias-RAG-1B can also be used in a broader range of non-conversational use cases including user support or educational assistance. Through this release, we aims to make SLMs workable in production by relying systematically on an externalized memory.