{ "architectures": [ "Qwen2MoeForCausalLM" ], "attention_dropout": 0.0, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 21, "model_type": "qwen2_moe", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 640000, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "4.56.1", "use_cache": false, "use_sliding_window": false, "vocab_size": 151936, "dtype": "bfloat16", "pad_token_id": 151643, "rope_scaling": null, "use_mrope": false, "decoder_sparse_step": 1, "moe_intermediate_size": 256, "shared_expert_intermediate_size": 8960, "num_experts_per_tok": 4, "num_experts": 32, "norm_topk_prob": false, "output_router_logits": false, "router_aux_loss_coef": 0.001 }