Create abstractive.py

abstractive.py

@@ -0,0 +1,16 @@
+# abstractive.py
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_name = "arousrihab/my-t5base-model"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+def abstractive_summary(text, max_length_ratio=0.2, min_length_ratio=0.1):
+    total_length = len(text.split())
+    max_length = int(total_length * max_length_ratio)
+    min_length = int(total_length * min_length_ratio)
+    
+    inputs = tokenizer.encode("summarize: " + text, return_tensors="pt", max_length=512, truncation=True)
+    summary_ids = model.generate(inputs, max_length=max_length, min_length=min_length, length_penalty=2.0, num_beams=4, early_stopping=True)
+    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+    return summary