Update app.py

app.py

@@ -9,7 +9,6 @@ from huggingface_hub import hf_hub_download #load from huggingfaces
 llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/airoboros-l2-13b-gpt4-m2.0-GGML", filename="airoboros-l2-13b-gpt4-m2.0.ggmlv3.q6_K.bin"), n_ctx=2048) #download model from hf/ n_ctx=2048 for high ccontext length
 
 history = []
-h = []
 history.append(["Hi there!", "Hello, how can I help you?"])
 
 def generate_text(input_text, history):
@@ -20,30 +19,26 @@ def generate_text(input_text, history):
     response = output['choices'][0]['text']
     history.append([input_text, response])
     
-    return "", history
-
-def bot(history):
-        bot_message = history
-        h[-1][1] = ""
-        for character in bot_message:
-            history[-1][1] += character
-            time.sleep(0.05)
-            yield h  
+    return "", response
 
+def bot(response):
+    history[-1][1] = ""
+    for character in response:
+        history[-1][1] += character
+        time.sleep(0.05)
+        yield history
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
     msg = gr.Textbox()
     clear = gr.ClearButton([msg, chatbot])
 
-    msg.submit(generate_text, [msg, chatbot], [msg, chatbot]).then(
+     msg.submit(generate_text, [msg, chatbot], [msg, chatbot], queue=False).then(
         bot, chatbot, chatbot
     )
-    clear.click(lambda: None, None, chatbot, queue=False)
 
+demo.queue()
 demo.launch()
 
 
 
-
-