Update README.md

README.md

@@ -168,33 +168,18 @@ A sequence-to-sequence model fine-tuned to extract structured event summaries fr
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import torch, json
 
-model_id = "your-namespace/your-model-repo"
+model_id = "https://huggingface.co/z-dickson/BART_political_event_detection"
 tok = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForSeq2SeqLM.from_pretrained(model_id).to("cuda" if torch.cuda.is_available() else "cpu")
-model.eval()
 
-text = "Following the devastating floods in Slovenia, our party calls for stronger climate resilience measures."
-enc = tok(text, return_tensors="pt", truncation=True, max_length=1024).to(model.device)
-gen = model.generate(**enc, max_new_tokens=128, num_beams=4, do_sample=False)
-out = tok.decode(gen[0], skip_special_tokens=True)
-
-# Safe parse
-def parse_json(s):
-    try: return json.loads(s)
-    except Exception:
-        if "{" in s and "}" in s:
-            s2 = s[s.find("{"): s.rfind("}")+1]
-            try: return json.loads(s2)
-            except Exception: pass
-        return None
-
-print(out)
-print(parse_json(out))
-```
 
-## Expected output example
+text = "Following the devastating floods in Slovenia, our party calls for stronger climate resilience measures."
+inputs = tok(text, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=128)
+response = tok.decode(outputs[0], skip_special_tokens=True)
+response_json = json.loads(response)
+response_json
 
-```{json}
 {
   "response_to_event": "Yes",
   "event_name": "Floods in Slovenia",
@@ -207,3 +192,4 @@ print(parse_json(out))
 
 
 
+