Update app.py

app.py

@@ -1,16 +1,12 @@
 import gradio as gr
 from llama_cpp import Llama
 
-
+llm = Llama(model_path="eachadea_ggml-vic7b-q4_0.bin", n_ctx=2048)
 
 def generate_text(prompt):
-    llm = Llama(model_path="eachadea_ggml-vic7b-q4_0.bin", n_ctx=2048)
     output = llm(prompt, max_tokens=468, temperature=0.1, top_p=0.5, echo=False, stop=["#"])
-    text = output['choices'][0]['text']
-    return text
-
-input_text = gr.Textbox(lines= 10, label="Enter your input text")
-output_text = gr.Textbox(label="Output text")
+    output_text = output['choices'][0]['text']
+    return output_text
 
 description = "Vicuna-7B-GPTQ-4bit-128g.GGML, max_tokens=468, temperature=0.1, top_p=0.5"
 
@@ -20,4 +16,10 @@ examples = [
     ["What is the square root of 64?", "The square root of 64 is 8."]
 ]
 
-demo = gr.Interface(fn=generate_text, inputs=input_text, outputs=output_text, title="Vicuna Language Model", description=description).launch()
+gradio_interface = gr.Interface(
+  fn=generate_text,
+  inputs="text",
+  outputs="text",
+  title="Vicuna API",
+)
+gradio_interface.launch()