config.json

{
  "architectures": [
    "DeepseekV4ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "eos_token_id": [
    1,
    128803
  ],
  "expert_dtype": "fp4",
  "hc_eps": 1e-06,
  "hc_mult": 4,
  "hc_sinkhorn_iters": 20,
  "head_dim": 512,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "index_head_dim": 128,
  "index_n_heads": 64,
  "index_topk": 512,
  "initializer_range": 0.02,
  "max_position_embeddings": 1048576,
  "model_type": "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_hash_layers": 3,
  "num_key_value_heads": 1,
  "num_nextn_predict_layers": 1,
  "o_groups": 8,
  "o_lora_rank": 1024,
  "q_lora_rank": 1024,
  "qk_rope_head_dim": 64,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000,
  "routed_scaling_factor": 1.5,
  "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,
  "compress_rope_theta": 160000,
  "compress_ratios": [
    0,
    0,
    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
  ],
  "rope_parameters": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 16.0,
    "original_max_position_embeddings": 65536,
    "rope_type": "yarn",
    "rope_theta": 10000.0
  },
  "quantization": {
    "bits": 8,
    "group_size": 32,
    "mode": "affine",
    "routed_expert_bits": 2,
    "routed_expert_bit_plan": {
      "default_bits": 2,
      "codec": "mxtq"
    },
    "mxtq_bits": {
      "routed_expert": 2,
      "attention": 8,
      "shared_expert": 8,
      "compressor": 8,
      "indexer": 8,
      "embed_tokens": 8,
      "lm_head": 8,
      "norms_router_hc": 16
    }
  },
  "weight_format": "mxtq",
  "routed_expert_bits": 2,
  "routed_expert_bit_plan": {
    "default_bits": 2,
    "codec": "mxtq"
  },
  "mxtq_bits": {
    "routed_expert": 2,
    "attention": 8,
    "shared_expert": 8,
    "compressor": 8,
    "indexer": 8,
    "embed_tokens": 8,
    "lm_head": 8,
    "norms_router_hc": 16
  },
  "mxtq_seed": 42,
  "group_size": 32,
  "_name_or_path": "DSV4-Flash-JANGTQ2"
}