Update app.py

app.py

@@ -31,20 +31,20 @@ def output_inference(tanya, history):
     prompt = prompt_template.format(ask=tanya)
     
     output = llm(
-        repeat_penalty=1.2,
-        prompt,
-        stop=["<|end_of_text|>"],
-        max_tokens=512,
-        temperature=0.3,
-        top_p=0.95,
-        top_k=40,
-        min_p=0.05,
-        typical_p=1.0,
-        stream=True)    
+    prompt,
+    stop=["<|end_of_text|>"],
+    max_tokens=512,
+    temperature=0.3,
+    top_p=0.95,
+    top_k=40,
+    min_p=0.05,
+    typical_p=1.0,
+    stream=True,
+    )    
     for out in output:
-        stream = copy.deepcopy(out)
-        temp += stream["choices"][0]["text"]
-        yield temp
+      stream = copy.deepcopy(out)
+      temp += stream["choices"][0]["text"]
+      yield temp
     
     history = ["init", prompt]