{ "architectures": [ "AfmoeModel" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "dtype": "float32", "eos_token_id": 3, "global_attn_every_n_layers": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 16, "layer_types": [ "sliding_attention", "full_attention" ], "max_position_embeddings": 200, "model_type": "afmoe", "moe_intermediate_size": 16, "mup_enabled": false, "num_attention_heads": 16, "num_dense_layers": 1, "num_experts": 4, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 16, "num_shared_experts": 2, "output_router_logits": false, "pad_token_id": 12, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 10000.0, "rope_type": "default" }, "route_scale": 1.0, "sliding_window": 128, "tie_word_embeddings": false, "transformers_version": "5.16.0.dev0", "use_cache": false, "vocab_size": 200000 }