{
  "architectures": [
    "HunYuanVLForConditionalGeneration"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_head_dim": 128,
  "bos_token_id": 120000,
  "dtype": "bfloat16",
  "eod_token_id": 120020,
  "eos_token_id": 120020,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "image_end_token_id": 120119,
  "image_newline_token_id": 120121,
  "image_start_token_id": 120118,
  "image_token_id": 120120,
  "initializer_range": 0.02,
  "intermediate_size": 3584,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "hunyuan_vl",
  "norm_type": "rms",
  "num_attention_heads": 16,
  "num_experts": 1,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "org_vocab_size": 120818,
  "pad_id": 120002,
  "pad_token_id": 120002,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "alpha": 1000.0,
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 1.0,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "type": "xdrope",
    "xdrope_section": [
      16,
      16,
      16,
      16
    ]
  },
  "rope_theta": 10000.0,
  "routed_scaling_factor": 1.0,
  "sep_token_id": 0,
  "text_config": {
    "_name_or_path": "/jizhicfs/shangppeng/save_models/hunyuan/HYOCR_1_5/std_hf/HYOCR_v1_5_SFT/0625_sft_stage2_step300",
    "add_classification_head": false,
    "architectures": [
      "HunYuanVLForConditionalGeneration"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_head_dim": 128,
    "bos_token_id": 120000,
    "class_num": 0,
    "dense_list": [
      1024,
      0
    ],
    "dtype": "bfloat16",
    "eod_token_id": 120020,
    "eos_token_id": 120007,
    "expert_hidden_dim": null,
    "first_k_dense_replace": 0,
    "group_limited_greedy": false,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "image_newline_token_id": 120121,
    "initializer_range": 0.02,
    "intermediate_size": 3584,
    "kv_lora_rank": 512,
    "mask_init_id": 13,
    "max_position_embeddings": 131072,
    "mlp_bias": false,
    "model_type": "hunyuan_vl_text",
    "moe_drop_tokens": false,
    "moe_intermediate_size": null,
    "moe_layer_num_skipped": 0,
    "moe_random_routing_dropped_token": false,
    "moe_topk": 1,
    "mtp_loss_factor": 0.1,
    "mtp_no_bias": true,
    "n_group": null,
    "norm_topk_prob": true,
    "norm_type": "rms",
    "num_attention_heads": 16,
    "num_experts": 1,
    "num_experts_per_tok": 1,
    "num_hidden_layers": 24,
    "num_key_value_heads": 8,
    "num_nextn_predict_layers": 1,
    "num_predictor_layers": 0,
    "num_shared_expert": 1,
    "num_shared_experts": 1,
    "org_vocab_size": 120818,
    "pad_id": 120002,
    "pad_token_id": 120002,
    "pool_type": "last",
    "pretraining_tp": 1,
    "q_lora_rank": 1536,
    "qk_nope_head_dim": 128,
    "qk_norm": false,
    "qk_rope_head_dim": 64,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "alpha": 1000.0,
      "beta_fast": 32,
      "beta_slow": 1,
      "factor": 1.0,
      "mscale": 1.0,
      "mscale_all_dim": 1.0,
      "type": "xdrope",
      "xdrope_section": [
        16,
        16,
        16,
        16
      ]
    },
    "rope_theta": 10000.0,
    "routed_scaling_factor": 1.0,
    "sep_token_id": 0,
    "text_end_id": 8,
    "text_start_id": 7,
    "tie_word_embeddings": true,
    "topk_group": null,
    "use_cache": true,
    "use_cla": false,
    "use_mixed_mlp_moe": false,
    "use_mla": false,
    "use_qk_norm": true,
    "use_rotary_pos_emb": true,
    "v_head_dim": 128,
    "vision_full_attention": false,
    "vocab_size": 120818
  },
  "text_end_id": 8,
  "text_start_id": 7,
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_cla": false,
  "use_qk_norm": true,
  "video_end_token_id": 120123,
  "video_start_token_id": 120122,
  "vision_config": {
    "add_patchemb_bias": true,
    "anyres_vit_max_image_size": 2048,
    "attention_dropout": 0.0,
    "cat_extra_token": 1,
    "dtype": "bfloat16",
    "hidden_act": "gelu",
    "hidden_dropout": 0.0,
    "hidden_size": 1152,
    "img_max_token_num": 16384,
    "intermediate_size": 4304,
    "interpolate_mode": "bilinear",
    "learnable_mlp_pooling_size": 0,
    "max_image_size": 2048,
    "max_vit_seq_len": 65536,
    "min_image_size": 512,
    "model_type": "hunyuan_vl",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "num_key_value_heads": 16,
    "out_hidden_size": 1024,
    "patch_size": 16,
    "perceive_post_norm": true,
    "perceive_pre_norm": true,
    "remove_prenorm": true,
    "resize_resolution": 2048,
    "rms_norm_eps": 1e-05,
    "spatial_merge_size": 2,
    "spatial_patch_size": 1,
    "temporal_patch_size": 1,
    "text_hidden_size": 1024,
    "video_max_image_size": 768,
    "video_min_image_size": 256,
    "vision_full_attention": false
  },
  "vocab_size": 120818
}