{
  "architectures": [
    "DeepseekV4ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "compress_ratios": [
    128,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    128,
    4,
    0
  ],
  "compress_rope_theta": 160000,
  "eos_token_id": 1,
  "expert_dtype": "fp8",
  "hc_eps": 1e-06,
  "hc_mult": 4,
  "hc_sinkhorn_iters": 20,
  "head_dim": 512,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "index_head_dim": 128,
  "index_n_heads": 64,
  "index_topk": 1024,
  "initializer_range": 0.02,
  "max_position_embeddings": 1048576,
  "mergehell_latest_indexer_patch": {
    "index_head_dim": 128,
    "index_n_heads": 64,
    "note": "Sparse attention indexer tensors were replaced with native DeepSeek-V4-Pro instruct indexer tensors. The merged checkpoint keeps widened main attention heads, but the indexer now uses the trained 64-head instruct retrieval policy.",
    "patch": "use_native_instruct_sparse_indexer",
    "patch_shard": "model-instruct-indexer64-patch.safetensors",
    "patched_at_utc": "2026-05-29T05:36:52Z",
    "previous_index_n_heads": 128,
    "source_layer_for_target_layer": {
      "10": 10,
      "12": 12,
      "14": 14,
      "16": 16,
      "18": 18,
      "2": 2,
      "20": 20,
      "22": 22,
      "24": 24,
      "26": 26,
      "28": 28,
      "30": 30,
      "32": 32,
      "34": 34,
      "36": 36,
      "38": 38,
      "4": 4,
      "40": 40,
      "42": 42,
      "44": 44,
      "46": 46,
      "48": 48,
      "50": 50,
      "52": 52,
      "54": 54,
      "56": 56,
      "58": 58,
      "6": 6,
      "60": 60,
      "8": 8
    },
    "source_model": "/home/shared/models/DeepSeek-V4-Pro",
    "target_layer_count": 30,
    "target_layers": [
      2,
      4,
      6,
      8,
      10,
      12,
      14,
      16,
      18,
      20,
      22,
      24,
      26,
      28,
      30,
      32,
      34,
      36,
      38,
      40,
      42,
      44,
      46,
      48,
      50,
      52,
      54,
      56,
      58,
      60
    ],
    "tensor_families": [
      "attn.indexer.wq_b.weight",
      "attn.indexer.wq_b.scale",
      "attn.indexer.weights_proj.weight",
      "attn.indexer.compressor.wkv.weight",
      "attn.indexer.compressor.wgate.weight",
      "attn.indexer.compressor.norm.weight",
      "attn.indexer.compressor.ape"
    ]
  },
  "mergehell_patch_history": [
    {
      "index_head_dim": 128,
      "index_n_heads": 64,
      "note": "Sparse attention indexer tensors were replaced with native DeepSeek-V4-Pro instruct indexer tensors. The merged checkpoint keeps widened main attention heads, but the indexer now uses the trained 64-head instruct retrieval policy.",
      "patch": "use_native_instruct_sparse_indexer",
      "patch_shard": "model-instruct-indexer64-patch.safetensors",
      "patched_at_utc": "2026-05-29T05:36:52Z",
      "previous_index_n_heads": 128,
      "source_layer_for_target_layer": {
        "10": 10,
        "12": 12,
        "14": 14,
        "16": 16,
        "18": 18,
        "2": 2,
        "20": 20,
        "22": 22,
        "24": 24,
        "26": 26,
        "28": 28,
        "30": 30,
        "32": 32,
        "34": 34,
        "36": 36,
        "38": 38,
        "4": 4,
        "40": 40,
        "42": 42,
        "44": 44,
        "46": 46,
        "48": 48,
        "50": 50,
        "52": 52,
        "54": 54,
        "56": 56,
        "58": 58,
        "6": 6,
        "60": 60,
        "8": 8
      },
      "source_model": "/home/shared/models/DeepSeek-V4-Pro",
      "target_layer_count": 30,
      "target_layers": [
        2,
        4,
        6,
        8,
        10,
        12,
        14,
        16,
        18,
        20,
        22,
        24,
        26,
        28,
        30,
        32,
        34,
        36,
        38,
        40,
        42,
        44,
        46,
        48,
        50,
        52,
        54,
        56,
        58,
        60
      ],
      "tensor_families": [
        "attn.indexer.wq_b.weight",
        "attn.indexer.wq_b.scale",
        "attn.indexer.weights_proj.weight",
        "attn.indexer.compressor.wkv.weight",
        "attn.indexer.compressor.wgate.weight",
        "attn.indexer.compressor.norm.weight",
        "attn.indexer.compressor.ape"
      ]
    }
  ],
  "model_type": "deepseek_v4",
  "moe_intermediate_size": 3072,
  "n_routed_experts": 768,
  "n_shared_experts": 2,
  "norm_topk_prob": true,
  "num_attention_heads": 256,
  "num_experts_per_tok": 12,
  "num_hash_layers": 3,
  "num_hidden_layers": 61,
  "num_key_value_heads": 1,
  "num_nextn_predict_layers": 1,
  "o_groups": 32,
  "o_lora_rank": 1024,
  "q_lora_rank": 1536,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "activation_scheme": "dynamic",
    "fmt": "e4m3",
    "ignored_layers": [
      "model.layers.0.attn.fused_wqa_wkv",
      "model.layers.1.attn.fused_wqa_wkv",
      "model.layers.2.attn.fused_wqa_wkv",
      "model.layers.3.attn.fused_wqa_wkv",
      "model.layers.4.attn.fused_wqa_wkv",
      "model.layers.5.attn.fused_wqa_wkv",
      "model.layers.6.attn.fused_wqa_wkv",
      "model.layers.7.attn.fused_wqa_wkv",
      "model.layers.8.attn.fused_wqa_wkv",
      "model.layers.9.attn.fused_wqa_wkv",
      "model.layers.10.attn.fused_wqa_wkv",
      "model.layers.11.attn.fused_wqa_wkv",
      "model.layers.12.attn.fused_wqa_wkv",
      "model.layers.13.attn.fused_wqa_wkv",
      "model.layers.14.attn.fused_wqa_wkv",
      "model.layers.15.attn.fused_wqa_wkv",
      "model.layers.16.attn.fused_wqa_wkv",
      "model.layers.17.attn.fused_wqa_wkv",
      "model.layers.18.attn.fused_wqa_wkv",
      "model.layers.19.attn.fused_wqa_wkv",
      "model.layers.20.attn.fused_wqa_wkv",
      "model.layers.21.attn.fused_wqa_wkv",
      "model.layers.22.attn.fused_wqa_wkv",
      "model.layers.23.attn.fused_wqa_wkv",
      "model.layers.24.attn.fused_wqa_wkv",
      "model.layers.25.attn.fused_wqa_wkv",
      "model.layers.26.attn.fused_wqa_wkv",
      "model.layers.27.attn.fused_wqa_wkv",
      "model.layers.28.attn.fused_wqa_wkv",
      "model.layers.29.attn.fused_wqa_wkv",
      "model.layers.30.attn.fused_wqa_wkv",
      "model.layers.31.attn.fused_wqa_wkv",
      "model.layers.32.attn.fused_wqa_wkv",
      "model.layers.33.attn.fused_wqa_wkv",
      "model.layers.34.attn.fused_wqa_wkv",
      "model.layers.35.attn.fused_wqa_wkv",
      "model.layers.36.attn.fused_wqa_wkv",
      "model.layers.37.attn.fused_wqa_wkv",
      "model.layers.38.attn.fused_wqa_wkv",
      "model.layers.39.attn.fused_wqa_wkv",
      "model.layers.40.attn.fused_wqa_wkv",
      "model.layers.41.attn.fused_wqa_wkv",
      "model.layers.42.attn.fused_wqa_wkv",
      "model.layers.43.attn.fused_wqa_wkv",
      "model.layers.44.attn.fused_wqa_wkv",
      "model.layers.45.attn.fused_wqa_wkv",
      "model.layers.46.attn.fused_wqa_wkv",
      "model.layers.47.attn.fused_wqa_wkv",
      "model.layers.48.attn.fused_wqa_wkv",
      "model.layers.49.attn.fused_wqa_wkv",
      "model.layers.50.attn.fused_wqa_wkv",
      "model.layers.51.attn.fused_wqa_wkv",
      "model.layers.52.attn.fused_wqa_wkv",
      "model.layers.53.attn.fused_wqa_wkv",
      "model.layers.54.attn.fused_wqa_wkv",
      "model.layers.55.attn.fused_wqa_wkv",
      "model.layers.56.attn.fused_wqa_wkv",
      "model.layers.57.attn.fused_wqa_wkv",
      "model.layers.58.attn.fused_wqa_wkv",
      "model.layers.59.attn.fused_wqa_wkv",
      "model.layers.60.attn.fused_wqa_wkv",
      "model.mtp.0.attn.fused_wqa_wkv"
    ],
    "quant_method": "fp8",
    "scale_fmt": "ue8m0",
    "weight_block_size": [
      128,
      128
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 16,
    "original_max_position_embeddings": 65536,
    "type": "yarn"
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "scoring_func": "sqrtsoftplus",
  "sliding_window": 128,
  "swiglu_limit": 10.0,
  "tie_word_embeddings": false,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.57.1",
  "use_cache": true,
  "vocab_size": 129280
}