update

app.py

@@ -7,10 +7,11 @@ For more information on `huggingface_hub` Inference API support, please check th
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("Moreza009/aya23-8b-double-quantized")
-model = AutoModelForCausalLM.from_pretrained("Moreza009/aya23-8b-double-quantized",device_map="auto")
-
+model_id = "MaziyarPanahi/Mistral-7B-Instruct-Aya-101-GGUF"
+filename = "Mistral-7B-Instruct-Aya-101.Q8_0.gguf"
 
+tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
 def respond(
     message,
     max_new_tokens=4000,