q4 model fast

app.py

@@ -1,17 +1,17 @@
 import gradio as gr
 
-from llama_cpp import Llama, LlamaTokenizer
-
-# llm = Llama.from_pretrained(
-#    repo_id="ID2223JR/gguf_model",
-#    filename="unsloth.Q4_K_M.gguf",
-# )
+from llama_cpp import Llama
 
 llm = Llama.from_pretrained(
-    repo_id="ID2223JR/gguf_model_q8",
-    filename="unsloth.Q8_0.gguf",
+    repo_id="ID2223JR/gguf_model",
+    filename="unsloth.Q4_K_M.gguf",
 )
 
+# llm = Llama.from_pretrained(
+#    repo_id="ID2223JR/gguf_model_q8",
+#    filename="unsloth.Q8_0.gguf",
+# )
+
 
 # Data storage
 ingredients_list = []