qwen-2.5-0.5b

exo/models.py

@@ -63,6 +63,7 @@ model_cards = {
   ### llava
   "llava-1.5-7b-hf": { "layers": 32, "repo": { "MLXDynamicShardInferenceEngine": "llava-hf/llava-1.5-7b-hf", }, },
   ### qwen
+  "qwen-2.5-0.5b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-0.5B-Instruct-4bit", }, },
   "qwen-2.5-coder-1.5b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-1.5B-Instruct-4bit", }, },
   "qwen-2.5-coder-3b": { "layers": 36, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-3B-Instruct-4bit", }, },
   "qwen-2.5-coder-7b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit", }, },