Update app.py

app.py

@@ -1,5 +1,4 @@
 import gradio as gr
-
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_path = "Wonder-Griffin/ShorseyBeerLeague"
@@ -11,13 +10,9 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype='auto'
 ).eval()
 
-input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
-respond = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
-
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
@@ -33,19 +28,11 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
+    input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+    output_ids = model.generate(input_ids.to('cuda'))
     respond = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        respond += token
-        yield respond
+    return respond
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -64,8 +51,4 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",
         ),
     ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+)