Update config.json

config.json

@@ -1,7 +1,8 @@
 {
   "architectures": [
-    "Qwen2MoeForCausalLM"
+    "Qwen3MoeForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "decoder_sparse_step": 1,
@@ -10,11 +11,11 @@
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 5504,
-  "max_position_embeddings": 1048576,
-  "max_window_layers": 28,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
   "mlp_only_layers": [],
-  "model_type": "qwen2_moe",
+  "model_type": "qwen3_moe",
   "moe_intermediate_size": 768,
   "norm_topk_prob": true,
   "num_attention_heads": 32,
@@ -23,18 +24,15 @@
   "num_hidden_layers": 48,
   "num_key_value_heads": 4,
   "output_router_logits": false,
-  "qkv_bias": false,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000000,
-  "router_aux_loss_coef": 0.0,
-  "shared_expert_intermediate_size": 0,
+  "router_aux_loss_coef": 0.001,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.3",
+  "transformers_version": "4.51.0",
   "use_cache": true,
-  "use_qk_norm": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}
+}