Update app.py

app.py

@@ -6,10 +6,10 @@ from llama_cpp import Llama
 HF_TOKEN = os.environ.get("scalable")
 
 # 🧠 Your GGUF repo on Hugging Face
-MODEL_ID = "FatimaZh/llama-3.2-1b-merged-code-gguf"
+MODEL_ID = "FatimaZh/llama-3.2-1b-merged-code-gguf-v2"
 
 # ❗ Replace this with the EXACT gguf filename in that repo
-GGUF_FILENAME = "merged_fp16_code.gguf"  # <-- CHANGE ME
+GGUF_FILENAME = "merged_fp16_code_v2.gguf"  # <-- CHANGE ME
 
 # 🧠 Load the GGUF model via llama-cpp
 llm = Llama.from_pretrained(