Merge pull request #423 from exo-explore/llama405b-8bit

add llama 3.1 405b 8bit at mlx-community/Meta-Llama-3.1-405B-Instruct…

exo/models.py

@@ -17,7 +17,7 @@ model_base_shards = {
     "TinygradDynamicShardInferenceEngine": Shard(model_id="NousResearch/Meta-Llama-3.1-70B-Instruct", start_layer=0, end_layer=0, n_layers=80),
   },
   "llama-3.1-405b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3.1-405B-4bit", start_layer=0, end_layer=0, n_layers=126),},
-  "llama-3.1-405b-8bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit", start_layer=0, end_layer=0, n_layers=126),},
+  "llama-3.1-405b-8bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3.1-405B-Instruct-8bit", 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),
     "TinygradDynamicShardInferenceEngine": Shard(model_id="TriAiExperiments/SFR-Iterative-DPO-LLaMA-3-8B-R", start_layer=0, end_layer=0, n_layers=32),