Update app.py

app.py

@@ -33,12 +33,8 @@ def generate(
 ):
     """run model inference, will return a Generator if streaming is true"""
 
-    return llm(
-        format_prompt(
-            user_prompt,
-        ),
-        **asdict(generation_config),
-    )
+    generator =  llm(format_prompt(user_prompt), **asdict(generation_config))
+    return generator.generated_text
 
 config = AutoConfig.from_pretrained(
     "teknium/Replit-v2-CodeInstruct-3B", context_length=2048
@@ -66,7 +62,7 @@ user_prefix = "[user]: "
 assistant_prefix = f"[assistant]:"
 
 title = "Replit-v2-CodeInstruct-3b-ggml"
-description = "This space is an attempt to run the 4 bit quantized version of 'Replit's CodeInstruct 3B' on CPU"
+description = "This space is an attempt to run the 4 bit quantized version of 'Replit's CodeInstruct 3B' on a CPU"
 
 example_1 = "Write a python script for a function which calculates the factorial of the number inputted by user."
 example_2 = "Write a python script which prints 'you are logged in' only if the user inputs a number between 1-10"
@@ -74,7 +70,7 @@ example_2 = "Write a python script which prints 'you are logged in' only if the
 examples = [example_1, example_2]
 
 UI = gr.Interface(
-    fn=lambda user_prompt: generate(llm, generation_config, user_prompt),
+    fn=generate,
     inputs=gr.Textbox(label="user_prompt", placeholder="Ask your queries here...."),
     outputs=gr.Textbox(label="Assistant"),
     title=title,