Update README.md

README.md

@@ -1,12 +1,17 @@
 ---
 library_name: transformers
-tags: []
+tags:
+  - rag
+  - retrieval-augmented-generation
+  - mcqa
+  - qwen3
+  - epfl
 ---
 
-# Model Card for Model ID
+# Model Card for EmaRimoldi/MNLP_M2_rag_model
 
 <!-- Provide a quick summary of what the model is/does. -->
-
+#This model is a fine-tuned Retrieval-Augmented Generation (RAG-Sequence) system, built to answer advanced STEM multiple-choice and short-answer questions by retrieving relevant context from a curated EPFL STEM corpus and then generating grounded answers.
 
 
 ## Model Details
@@ -15,23 +20,24 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Developed by:** Ema Rimoldi (EPFL CS-552 MNLP course)  
+- **Funded by [optional]:** EPFL Natural Language Processing Lab  
+- **Model type:** RAG-Sequence (Retrieval-Augmented Generation)  
+- **Language(s) (NLP):** English  
+- **License:** Apache-2.0  
+- **Finetuned from model [optional]:** Qwen3-0.6B-Base  
+
 
 ### Model Sources [optional]
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** https://huggingface.co/EmaRimoldi/MNLP_M2_rag_model  
+- **Dataset:** https://huggingface.co/datasets/EmaRimoldi/MNLP_M2_rag_dataset  
+- **Document encoder:** https://huggingface.co/EmaRimoldi/MNLP_M2_document_encoder  
+- **Retriever index:** FAISS index stored under https://huggingface.co/datasets/EmaRimoldi/MNLP_M2_documents  
+
 
 ## Uses
 
@@ -41,6 +47,24 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
+Call the RAG pipeline to ground answers in retrieved EPFL STEM documents:
+
+```python
+from transformers import RagTokenizer, RagSequenceForGeneration
+
+tokenizer = RagTokenizer.from_pretrained("EmaRimoldi/MNLP_M2_rag_model")
+model     = RagSequenceForGeneration.from_pretrained("EmaRimoldi/MNLP_M2_rag_model")
+
+input_dict = tokenizer.prepare_seq2seq_batch(
+    question="What is the Carnot engine?",
+    n_docs=5,
+    return_tensors="pt"
+)
+generated = model.generate(**input_dict)
+print(tokenizer.batch_decode(generated, skip_special_tokens=True))
+
+
+
 [More Information Needed]
 
 ### Downstream Use [optional]