Upload mlx/config.json with huggingface_hub

mlx/config.json

@@ -1,36 +1,37 @@
 {
     "architectures": [
-        "Qwen2ForCausalLM"
+        "Qwen3ForCausalLM"
     ],
+    "attention_bias": false,
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
     "eos_token_id": 151645,
+    "head_dim": 128,
     "hidden_act": "silu",
-    "hidden_size": 2048,
+    "hidden_size": 2560,
     "initializer_range": 0.02,
-    "intermediate_size": 11008,
-    "max_position_embeddings": 32768,
-    "max_window_layers": 70,
-    "model_type": "qwen2",
-    "num_attention_heads": 16,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
     "num_hidden_layers": 36,
-    "num_key_value_heads": 2,
+    "num_key_value_heads": 8,
     "quantization": {
         "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
+        "bits": 4
     },
     "quantization_config": {
         "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
+        "bits": 4
     },
     "rms_norm_eps": 1e-06,
-    "rope_theta": 1000000.0,
-    "sliding_window": 32768,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
     "tie_word_embeddings": true,
     "torch_dtype": "bfloat16",
-    "transformers_version": "4.43.1",
+    "transformers_version": "4.51.0",
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151936