Switch to llama

app.py

@@ -42,8 +42,8 @@ try:
     logger.info("SentenceTransformer model loaded")
 
     # Load Qwen 2.5 7B model
-    repo_id = "bartowski/Qwen2.5-7B-Instruct-GGUF"
-    filename = "Qwen2.5-7B-Instruct-Q4_K_M.gguf"
+    repo_id = "bartowski/Llama-3.2-3B-Instruct-GGUF" # "bartowski/Qwen2.5-7B-Instruct-GGUF"
+    filename = "Llama-3.2-3B-Instruct-Q6_K_L.gguf" # "Qwen2.5-7B-Instruct-Q4_K_M.gguf"
     logger.info(f"Loading {filename} model")
     model_path = hf_hub_download(
         repo_id=repo_id,