fix model id for llama 3.1 405b now its finally on the hub

exo/api/chatgpt_api.py

@@ -21,7 +21,7 @@ shard_mappings = {
     "MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3.1-70B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=80),
   },
   "llama-3.1-405b": {
-    "MLXDynamicShardInferenceEngine": Shard(model_id="/Users/alex/405b-instruct-4bit", start_layer=0, end_layer=0, n_layers=126),
+    "MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3.1-405B-4bit", start_layer=0, end_layer=0, n_layers=126),
   },
   "llama-3-8b": {
     "MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3-8B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=32),