Update README.md

model_cards/facebook/rag-sequence-nq/README.md

+---
+language: en
+license: apache-2.0
+datasets:
+- wiki_dpr
+---
 ## RAG
 
 This is the RAG-Sequence Model of the the paper [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/pdf/2005.11401.pdf) 
 by Patrick Lewis, Ethan Perez, Aleksandara Piktus et al.
 
-## Usage:
+The model is a *uncased* model, which means that capital letters are simply converted to lower-case letters.
 
-```python
+The model consits of a *question_encoder*, *retriever* and a *generator*. The retriever is extracts relevant passages from the *wiki_dpr* `train` datasets, which is linked above.
+The question_encoder and retriever are based on `facebook/dpr-question_encoder-single-nq-base` and `facebook/bart-large`, which were jointly finetuned on 
+on the *wiki_dpr* QA dataset in an end-to-end fashion.
 
-from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
+## Usage:
 
-tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
-retriever = RagRetriever.from_pretrained("facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True)
-model = RagSequenceForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever)
+**Note**: In the usage example below only the *dummy* retriever of *wiki_dpr* is used because the real retriever requires to over 40 GB of RAM.
+The model can generate questions to any question as follows:
 
-input_dict = tokenizer.prepare_seq2seq_batch("How many people live in Paris?", "In Paris, there are 10 million people.", return_tensors="pt")
-outputs = model(input_ids=input_dict["input_ids"], labels=input_dict["labels"])
+```python
 
-# outputs.loss should give 76.2978
+from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration 
+ 
+tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq") 
+retriever = RagRetriever.from_pretrained("facebook/rag-token-nq", index_name="exact", use_dummy_dataset=True) 
+model = RagSequenceForGeneration.from_pretrained("facebook/rag-token-nq", retriever=retriever) 
+ 
+input_dict = tokenizer.prepare_seq2seq_batch("how many countries are in europe", return_tensors="pt") 
 
-generated = model.generate(input_ids=input_dict["input_ids"])
-generated_string = tokenizer.batch_decode(generated, skip_special_tokens=True)
+generated = model.generate(input_ids=input_dict["input_ids"]) 
+print(tokenizer.batch_decode(generated, skip_special_tokens=True)[0]) 
 
-# generated_string should give 270,000,000 -> not quite correct the answer, but it also only uses a dummy index
+# should give 54 => google says either 44 or 51
 ```