Update app.py

app.py

@@ -19,17 +19,18 @@ model = AutoModelForCausalLM.from_pretrained(model_path, device_map='cuda', quan
 
 @spaces.GPU
 def generate_text(usertitle, content, max_new_tokens=512,model=model, tokenizer=tokenizer, temperature=0.7):
-    msg = [{
-        'title': title,
-        'content': content
-    }]
-    inputs = tokenizer.apply_chat_template(msg, return_tensors='pt').cuda()
-    generated_ids = model.generate(inputs['input_ids'], max_new_tokens=max_new_tokens, temperature=temperature, pad_token_id=tokenizer.eos_token_id)
-    generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
+#   msg = [{
+#       'title': title,
+#       'content': content
+#   }]
+    input_text = f"[[[Title:]]]{usertitle}\n[[[Content:]]]{content}\n"
+    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)
     
     return generated_text
 
-
 def gradio_app():
     with gr.Blocks() as demo:
         gr.Markdown(title)