Merge branch 'main' of https://huggingface.co/domenicrosati/question_converter-3b

README.md

@@ -16,7 +16,7 @@ See:
 
 ## TL;DR:
 We fine-tune a seq2seq model,
-T5-3B (Raffel et al., 2020), using the $(a, q, d)$ pairs
+T5-3B (Raffel et al., 2020), using the (a, q, d) pairs
 annotated by Demszky et al. (2018).
 
 Where a is answer, q is question, and d is declerative sentence (i.e. a statement).
@@ -25,6 +25,8 @@ See Appendex B.2 of Chen et al. for more.
 
 ## Usage
 
+The prompt should be `{question} {seperator} {answer}` where the seperator is `</s>`.
+
 ```python
 from transformers import AutoTokenizer,  AutoModelForSeq2SeqLM
 
@@ -32,10 +34,11 @@ tokenizer = AutoTokenizer.from_pretrained('domenicrosati/question_converter-3b')
 model = AutoModelForSeq2SeqLM.from_pretrained('domenicrosati/question_converter-3b')
 
 question = "Where in the world is Carmen Sandiego?"
-answer = "She is in D'Abruzzo"
+answer = "She is in Abruzzo"
 
 prompt = f'{question} </s> {answer}'
 input_ids = tokenizer(prompt, return_tensors='pt').input_ids
 output_ids = model.generate(input_ids)
 responses = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
 ```
+> `['Carmen Sandiego is in Abruzzo.']`