{
  "architectures": [
    "RWKV7VLForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "modeling_modrwkv.ModRWKVConfig",
    "AutoModelForImageTextToText": "modeling_modrwkv.RWKV7VLForConditionalGeneration"
  },
  "dtype": "float32",
  "image_token_id": 65532,
  "model_type": "modrwkv",
  "projector_config": {
    "encoder_dim": 1024,
    "hidden_dim": null,
    "num_deepstack": 0,
    "project_dim": 1024,
    "projector_type": "visual"
  },
  "text_config": {
    "a_low_rank_dim": 64,
    "attn": null,
    "attn_mode": "chunk",
    "auto_map": {
      "AutoConfig": "configuration_rwkv7.RWKV7Config",
      "AutoModel": "modeling_rwkv7.RWKV7Model",
      "AutoModelForCausalLM": "modeling_rwkv7.RWKV7ForCausalLM"
    },
    "bos_token_id": 23,
    "decay_low_rank_dim": 64,
    "dtype": "bfloat16",
    "eos_token_id": 24,
    "fuse_cross_entropy": false,
    "fuse_linear_cross_entropy": false,
    "fuse_norm": true,
    "gate_low_rank_dim": 128,
    "head_dim": 64,
    "hidden_act": "sqrelu",
    "hidden_ratio": 4,
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "max_position_embeddings": 8192,
    "model_type": "rwkv7",
    "norm_bias": true,
    "norm_eps": 1e-05,
    "norm_first": true,
    "num_attention_heads": 16,
    "num_heads": 16,
    "num_hidden_layers": 24,
    "pad_token_id": 24,
    "tie_word_embeddings": false,
    "use_cache": true,
    "use_l2warp": true,
    "v_low_rank_dim": 32,
    "value_dim": [
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024,
      1024
    ],
    "vocab_size": 65536
  },
  "tie_word_embeddings": false,
  "transformers_version": "5.8.0",
  "use_conv_in_projector": false,
  "vision_config": {
    "deepstack_visual_indexes": [],
    "depth": 12,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "model_type": "qwen3_vl_vision",
    "num_heads": 12,
    "num_position_embeddings": 2304,
    "out_hidden_size": 1024,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 65531,
  "vision_start_token_id": 65530
}