Update app.py

app.py

@@ -46,27 +46,23 @@ Image: [IMAGE]
 Description: """
     
     # Tokenize input
-    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
     
     # Generate response
     with torch.no_grad():
         outputs = model.generate(
-            input_ids=inputs['input_ids'],  # Explicitly use input_ids
-            attention_mask=inputs['attention_mask'],  # Add attention mask
-            max_new_tokens=max_length,
+            **inputs,
+            max_length=max_length,
             temperature=temperature,
             top_p=top_p,
             do_sample=True,
+            num_return_sequences=1,
             pad_token_id=tokenizer.pad_token_id,
-            bos_token_id=tokenizer.bos_token_id,
-            eos_token_id=tokenizer.eos_token_id,
-            use_cache=True,  # Enable caching
-            return_dict_in_generate=True,  # Return as dict
-            output_scores=True  # Get scores
+            eos_token_id=tokenizer.eos_token_id
         )
     
     # Decode and return the response
-    generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=True)
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return generated_text.split("Description: ")[-1].strip()
 
 def create_demo(model_id):