Update app.py

app.py

@@ -4,8 +4,8 @@ import time
 
 # Load your LLaMA model with GPU support, quantization, and multi-threading
 llm = Llama.from_pretrained(
-    repo_id="Ahil1991/Bee-V.01-7B",
-    filename="Bee-V.01.gguf",
+    repo_id="Ahil1991/Bee-8.3B",
+    filename="Bee 8.3B Q4_K_M.gguf",
     use_gpu=True,  # Enable GPU if available
     quantize="4bit",  # Quantization for speed (4-bit or 8-bit, adjust based on needs)
     num_threads=4  # Adjust based on CPU cores available (only for CPU use)