config.json

{
  "architectures": [
    "DeepSeekV4VisionForConditionalGeneration"
  ],
  "bos_token_id": 0,
  "eos_token_id": 1,
  "ignore_index": -100,
  "media_placeholder_token_id": 129279,
  "model_type": "deepseek_v4_vision",
  "text_config": {
    "architectures": [
      "DeepseekV4ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "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,
      0,
      0
    ],
    "compress_rope_theta": 160000,
    "dspark_block_size": 5,
    "dspark_markov_rank": 256,
    "dspark_noise_token_id": 128799,
    "dspark_target_layer_ids": [
      40,
      41,
      42
    ],
    "eos_token_id": 1,
    "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,
    "keep_packed_fp4_experts": true,
    "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_hash_layers": 3,
    "num_hidden_layers": 43,
    "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,
    "quantization_config": {
      "activation_scheme": "dynamic",
      "fmt": "e4m3",
      "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": 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
  },
  "torch_dtype": "bfloat16",
  "use_unified_vision_chunk": true,
  "video_placeholder": "<|dsv4_vision_video_placeholder|>",
  "vision_config": {
    "hidden_size": 1152,
    "init_pos_emb_height": 64,
    "init_pos_emb_time": 4,
    "init_pos_emb_width": 64,
    "intermediate_size": 4304,
    "merge_kernel_size": [
      2,
      2
    ],
    "merge_type": "sd2_tpool",
    "mm_hidden_size": 4096,
    "mm_projector_type": "patchmerger",
    "model_type": "kimi_k25_vision",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "pos_emb_type": "divided_fixed",
    "projector_hidden_act": "gelu",
    "projector_ln_eps": 1e-05,
    "text_hidden_size": 4096,
    "video_attn_type": "spatial_temporal",
    "vt_hidden_size": 1152,
    "vt_intermediate_size": 4304,
    "vt_num_attention_heads": 16,
    "vt_num_hidden_layers": 27
  }
}