| { | |
| "architectures": [ | |
| "Qwen3MoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "decoder_sparse_step": 1, | |
| "hidden_act": "silu", | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 48, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 768, | |
| "norm_topk_prob": false, | |
| "num_attention_heads": 32, | |
| "num_experts": 2, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 4, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 64 | |
| } | |