update

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
-
+import accelerate 
+import bitsandbytes
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
@@ -7,7 +8,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("Moreza009/aya23-8b-double-quantized")
-model = AutoModelForCausalLM.from_pretrained("Moreza009/aya23-8b-double-quantized")
+model = AutoModelForCausalLM.from_pretrained("Moreza009/aya23-8b-double-quantized",device_map="auto")
 
 
 def respond(

requirements.txt

@@ -1,3 +1,5 @@
+accelerate
+bitsandbytes
 torch 
 transformers
 huggingface_hub==0.22.2