Update app.py

app.py

@@ -18,14 +18,13 @@ quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 model = AutoModelForCausalLM.from_pretrained(model_path, device_map='cuda', quantization_config=quantization_config)
 
 @spaces.GPU
-def generate_text(usertitle, content, max_new_tokens=512, temperature=0.7, model=model, tokenizer=tokenizer):
+def generate_text(usertitle, content, max_new_tokens=512, temperature=0.7):
 #   msg = [{
 #       'title': title,
 #       'content': content
 #   }]
     input_text = f"[[[Title:]]]{usertitle}\n[[[Content:]]]{content}\n"
-    inputs = tokenizer(input_text, return_tensors='pt').to('cuda')
-    
+    inputs = tokenizer(input_text, return_tensors='pt').to('cuda')    
     generated_ids = model.generate(inputs['input_ids'], max_new_tokens=max_length, temperature=temperature, pad_token_id=tokenizer.eos_token_id)
     generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=False)