{
  "attention_dropout": 0.0,
  "compress_block_size": 32,
  "deltanet_chunk_size": 128,
  "deltanet_d_state": 64,
  "diff_lambda_init": 0.8,
  "diff_lambda_layer_decay": 0.6,
  "expert_intermediate_size": 512,
  "gdn_chunk_size": 64,
  "gdn_d_conv": 4,
  "gdn_expand": 1,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "hybrid_groupnorm_groups": 8,
  "hyena_dropout": 0.0,
  "hyena_filter_order": 64,
  "initializer_range": 0.02,
  "intermediate_size": 512,
  "linear_d_conv": 4,
  "linear_d_state": 64,
  "linear_expand": 1,
  "mamba2_chunk_size": 256,
  "mamba2_d_conv": 4,
  "mamba2_d_state": 128,
  "mamba2_expand": 2,
  "mamba2_headdim": 64,
  "max_position_embeddings": 8192,
  "mla_kv_lora_rank": 256,
  "mla_q_lora_rank": 768,
  "mla_qk_nope_head_dim": 64,
  "mla_qk_rope_head_dim": 64,
  "mla_v_head_dim": 128,
  "model_type": "aether_v2_11attn",
  "nsa_compress_block_size": 32,
  "nsa_select_top_k": 16,
  "nsa_sliding_window": 512,
  "num_attention_heads": 8,
  "num_experts": 25,
  "num_experts_per_tok": 7,
  "num_hidden_layers": 121,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "pad_token_id": 151643,
  "rezero_alpha_init": 0.0,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.01,
  "sliding_window_size": 1024,
  "tie_word_embeddings": false,
  "transformers_version": "5.3.0",
  "use_cache": false,
  "use_deepnet_init": true,
  "use_shared_expert": true,
  "vocab_size": 151936,
  "z_loss_coef": 0.001,
  "auto_map": {
    "AutoConfig": "configuration_aether_v2_11attn.AETHERV211AttnConfig",
    "AutoModelForCausalLM": "modeling_aether_v2_11way.AETHERV211AttnForCausalLM",
    "AutoModel": "modeling_aether_v2_11way.AETHERV211AttnModel"
  },
  "architectures": [
    "AETHERV211AttnForCausalLM"
  ],
  "cyclic_routing": true,
  "num_cyclic_phases": 5
}