{ "_name_or_path": "./moe-out", "architectures": [ "Qwen2MoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "decoder_sparse_step": 1, "eos_token_id": [ 128001, 128008, 128009 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "max_window_layers": 28, "mlp_bias": false, "mlp_only_layers": [], "model_type": "qwen2_moe", "moe_intermediate_size": 14336, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts": 2, "num_experts_per_tok": 2, "num_hidden_layers": 32, "num_key_value_heads": 8, "output_router_logits": false, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "router_aux_loss_coef": 0.001, "shared_expert_intermediate_size": 14336, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.46.3", "use_cache": true, "use_sliding_window": false, "vocab_size": 128256 }