Update app.py

app.py

@@ -1,15 +1,14 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from ctransformers import AutoModelForCausalLM
 import gradio as gr
 import random
 import time
 
+
+
 def call_chat(message):
-    model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    model = AutoModelForCausalLM.from_pretrained(model_id)
-    inputs = tokenizer(message, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=20)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    llm = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", model_type="Mistral")
+    for text in llm(message, stream=True):
+        return (message, end="", flush=True)
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()