Create README.md

README.md

@@ -0,0 +1,36 @@
+---
+language:
+- en
+metrics:
+- rouge
+---
+# Personalised opener
+  This model creates an opener based on a provided interest.
+### Model input
+> [INTEREST]
+### Example
+> dancing
+
+### Output
+> What's your favorite dance move to make people laugh or cry?
+
+### How to use in code
+```{python}
+import nltk
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+tokenizer = AutoTokenizer.from_pretrained("njvdnbus/personalised_opener-t5-large")
+model = AutoModelForSeq2SeqLM.from_pretrained("njvdnbus/personalised_opener-t5-large")
+
+def use_model(text):
+    inputs = ["" + text]
+    inputs = tokenizer(inputs, truncation=True, return_tensors="pt")
+    output = model.generate(**inputs, num_beams=1, do_sample=True, min_length=10, max_length=256)
+    decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
+    predicted_interests = nltk.sent_tokenize(decoded_output.strip())[0]
+    return predicted_interests
+
+text= "tennis"
+print(use_model(text))
+```
+
+> Do you think tennis is the most exciting sport out there?