Update app.py

app.py

@@ -13,26 +13,26 @@ base_model = AutoModelForCausalLM.from_pretrained(
 tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 
 # Load the Lora model
-model = PeftModel.from_pretrained(peft_model_id, base_model=base_model)
-
+model = PeftModel.from_pretrained(base_model, peft_model_id)
 
 def make_inference(question):
-  batch = tokenizer("### This is your question {}\n".format(question), return_tensors='pt')
-
-  with torch.cuda.amp.autocast():
-    output_tokens = model.generate(**batch, max_new_tokens=50)
+    input_text = "### This is your question {}\n".format(question)
+    batch = tokenizer(input_text, return_tensors='pt')
 
-  display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))
+    with torch.cuda.amp.autocast():
+        output_tokens = model.generate(**batch, max_length=50, num_return_sequences=1)
 
+    return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
 
 if __name__ == "__main__":
-    # make a gradio interface
     import gradio as gr
 
     gr.Interface(
         make_inference,
-        gr.inputs.Textbox(lines=2, label="Question"),
-        gr.outputs.Textbox(label="Answer"),
+        [
+            gr.inputs.Textbox(lines=2, label="Question"),
+            gr.outputs.Textbox(label="Answer")
+        ],
         title="BlackQA",
         description="Generated Text of Black heros",
     ).launch()