{
  "_name_or_path": "",
  "architectures": [
    "MemTDeepseekV4ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_memt.MemTDeepseekV4Config",
    "AutoModelForCausalLM": "modeling_memt.MemTDeepseekV4ForCausalLM"
  },
  "bos_token_id": 0,
  "chunk_size_feed_forward": 0,
  "compress_rates": {
    "compressed_sparse_attention": 4,
    "heavily_compressed_attention": 128
  },
  "compress_rope_theta": 160000,
  "dtype": "bfloat16",
  "eos_token_id": 1,
  "expert_dtype": "bf16",
  "hc_eps": 1e-06,
  "hc_mult": 4,
  "hc_sinkhorn_iters": 20,
  "head_dim": 512,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "index_head_dim": 128,
  "index_n_heads": 64,
  "index_topk": 512,
  "initializer_range": 0.02,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention",
    "heavily_compressed_attention",
    "compressed_sparse_attention"
  ],
  "max_position_embeddings": 1048576,
  "memt": {
    "chunk_tokens": 2048,
    "gate_latent_norm": false,
    "gate_rank": 512,
    "gdn_version": "stable_gdn2",
    "head_dim": 512,
    "kv_groups": 8,
    "kv_rank": 512,
    "layers": [
      4,
      6,
      8,
      10,
      12,
      14,
      16,
      18,
      20,
      22,
      24,
      26,
      28,
      30,
      32,
      34,
      36,
      38,
      40,
      42
    ],
    "memory_head_mode": "mha",
    "memory_read_scale": "k_inv_sqrt",
    "memory_update_mode": "token",
    "memory_use_short_conv": false,
    "norm_eps": 1e-06,
    "num_kv_heads": 64,
    "num_memory_heads": 64,
    "output_gate_bias": true,
    "output_gate_softcap_enabled": true,
    "output_gate_softcap_limit": 2.0,
    "output_gate_type": "silu",
    "projection": "grouped_kv_low_rank",
    "q_rank": 1024,
    "stable_gdn2_sqrt_erase_gate": true,
    "tail_policy": "commit"
  },
  "mlp_bias": false,
  "mlp_layer_types": [
    "hash_moe",
    "hash_moe",
    "hash_moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe",
    "moe"
  ],
  "model_type": "memt_deepseek_v4",
  "moe_intermediate_size": 2048,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 64,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 43,
  "num_key_value_heads": 1,
  "num_nextn_predict_layers": 0,
  "o_groups": 8,
  "o_lora_rank": 1024,
  "output_attentions": false,
  "output_hidden_states": false,
  "output_router_logits": false,
  "pad_token_id": 1,
  "partial_rotary_factor": 0.125,
  "problem_type": null,
  "q_lora_rank": 1024,
  "qk_rope_head_dim": 64,
  "return_dict": true,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "compress": {
      "attention_factor": 1.0,
      "beta_fast": 32,
      "beta_slow": 1,
      "factor": 16,
      "original_max_position_embeddings": 65536,
      "partial_rotary_factor": 0.125,
      "rope_theta": 160000,
      "rope_type": "yarn",
      "type": "yarn"
    },
    "main": {
      "partial_rotary_factor": 0.125,
      "rope_theta": 10000,
      "rope_type": "default"
    }
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 1.5,
  "router_aux_loss_coef": 0.001,
  "router_jitter_noise": 0.0,
  "scoring_func": "sqrtsoftplus",
  "sliding_window": 128,
  "swiglu_limit": 10.0,
  "tie_word_embeddings": false,
  "topk_method": "noaux_tc",
  "transformers_version": "5.12.1",
  "use_cache": true,
  "vocab_size": 129280
}