Update app.py

app.py

@@ -1,5 +1,7 @@
 import torch
 from transformers import LlamaForCausalLM, LlamaTokenizer
+import gradio as gr
+
 
 # Hugging Face model_path
 model_path = 'psmathur/orca_mini_3b'
@@ -10,7 +12,7 @@ model = LlamaForCausalLM.from_pretrained(
 
 
 #generate text function
-def predict(system, instruction, input=None):
+def generate_text(system, instruction, input=None):
 
     if input:
         prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
@@ -38,8 +40,6 @@ def predict(system, instruction, input=None):
     string = tokenizer.decode(output, skip_special_tokens=True)
     return f'[!] Response: {string}'
 
-import gradio as gr
-
 # Define input components
 prompt_input = gr.inputs.Textbox(label="System")
 instruction_input = gr.inputs.Textbox(label="Instruction")
@@ -49,7 +49,6 @@ context_input = gr.inputs.Textbox(label="Context")
 output_text = gr.outputs.Textbox(label="Output")
 
 # Create the interface
-iface=gr.Interface(fn=predict,
+gr.Interface(fn=generate_text,
                         inputs=[prompt_input, instruction_input, context_input],
-                        outputs=output_text,enable_queue=True)
-iface.launch()
+                        outputs=output_text,enable_queue=True).launch(debug=True)