{ "architectures": [ "Qwen3MoeForCausalLM" ], "model_type": "qwen3_moe", "vocab_size": 151936, "hidden_size": 1536, "intermediate_size": 8960, "moe_intermediate_size": 768, "num_hidden_layers": 28, "num_attention_heads": 12, "num_key_value_heads": 2, "head_dim": 64, "hidden_act": "silu", "max_position_embeddings": 32768, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "tie_word_embeddings": true, "rope_theta": 1000000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 28, "decoder_sparse_step": 1, "num_experts": 288, "num_experts_per_tok": 6, "norm_topk_prob": true, "output_router_logits": false, "router_aux_loss_coef": 0.001, "mlp_only_layers": [], "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "bos_token_id": 151643, "eos_token_id": 151645 }