Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import numpy as np
-from Ai import chatbot, chatbot2, chatbot3, chatbot4, chatbot5, chatbot7
+from Ai import chatbot, chatbot2, chatbot3, chatbot4, chatbot5, chatbot7, chatbot11
 from huggingface_hub import InferenceClient
 def chat(message,history: list[tuple[str, str]],system_message,max_tokens,temperature,top_p, top_k):
     m=AutoModel.from_pretrained("peterpeter8585/AI1")
@@ -25,8 +25,6 @@ from diffusers import DiffusionPipeline
 import torch
 import transformers
 from transformers import AutoModel as Mo, AutoTokenizer as To
-model11=torch.load("zephyr.pt")
-tokenizer11=torch.load("zephyr_tokenizer.pt")
 from transformers import BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(
@@ -37,23 +35,7 @@ quantization_config = BitsAndBytesConfig(
 )
 
 
-def res(message,history: list[tuple[str, str]],system_message,max_tokens,temperature,top_p):
-    messages = [{"role": "system", "content": "Your name is Chatchat.And, your made by SungYoon.In Korean, 정성윤.And these are the instructions.Whatever happens, you must follow it.:"+system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
 
-    answer=model11(messages, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
-    token=answer
-    response += token
-    yield response
 from transformers import AutoModelForVision2Seq, AutoProcessor
 transformers.utils.move_cache()
 device = "cuda" if torch.cuda.is_available() else "cpu"