Upload README.md

README.md

@@ -33,14 +33,18 @@ Here is how to use this model to classify a context-window of a dialogue:
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 import torch
 
+# Target utterance
 test_texts = ['Utterance2']
+# Bi-directional context of the target utterance
 test_text_pairs = ['Utterance1;Utterance2;Utterance3']
 
+# Load the model and tokenizer
 checkpoint_path = "chi2024/mt5-base-binary-cs-iiia"
 model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint_path)\
     .to("cuda" if torch.cuda.is_available() else "cpu")
 tokenizer = AutoTokenizer.from_pretrained(checkpoint_path)
 
+# Define helper functions
 def verbalize_input(text: str, text_pair: str) -> str:
     return "Utterance: %s\nContext: %s" % (text, text_pair)
 
@@ -53,6 +57,7 @@ def predict_one(text, pair):
                tokenizer.batch_decode(outputs, skip_special_tokens=True)]
     return decoded
 
+# Run the prediction
 preds_txt = [predict_one(t,p) for t,p in zip(test_texts, test_text_pairs)]
 preds_lbl = [1 if x == 'positive' else 0 for x in preds_txt]
 print(preds_lbl)