feat: change to a lighter model

app.py

@@ -6,8 +6,8 @@ from uuid import uuid4
 
 # repo_id = "Qwen/Qwen2.5-0.5B-Instruct-GGUF"
 # filename = "qwen2.5-0.5b-instruct-q8_0.gguf"
-repo_id = "MaziyarPanahi/Qwen2.5-7B-Instruct-GGUF"
-filename = "Qwen2.5-7B-Instruct.Q4_K_S.gguf"
+repo_id = "Qwen/Qwen2.5-3B-Instruct-GGUF"
+filename = "qwen2.5-3b-instruct-q5_k_m.gguf"
 
 llm = load_llm(repo_id, filename)