Update model_usage.py

model_usage.py

@@ -20,11 +20,15 @@ for prompt in prompts:
     inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
     with torch.no_grad():
         outputs = model.generate(
-            inputs,
-            max_new_tokens=50,
-            temperature=0.8,
-            top_p=0.9,
-            do_sample=True
-        )
+        input_ids,
+        max_new_tokens=60,          
+        temperature=0.7,             
+        top_p=0.9,
+        top_k=50,                   
+        repetition_penalty=1.2,      
+        no_repeat_ngram_size=3,      
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
     text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     print(f"{text}\n")