{
  "_attn_implementation": "flash_attention_2",
  "_attn_implementation_autoset": false,
  "answer_start_pattern": [
    151644,
    77091
  ],
  "architectures": [
    "Eagle3_VLForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_eagle3_vl.Eagle3_VLConfig",
    "AutoModel": "modeling_eagle3_vl.Eagle3_VLForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_eagle3_vl.Eagle3_VLForConditionalGeneration"
  },
  "downsample_ratio": 0.5,
  "dtype": "bfloat16",
  "dynamic_image_size": false,
  "eos_token_id": 151645,
  "image_token_index": 151669,
  "initializer_range": 0.02,
  "latent_end_id": 151682,
  "latent_start_id": 151681,
  "latent_token_id": 151680,
  "loss_type": "ForCausalLMLoss",
  "loss_version": "efficient_v2_cp_head",
  "max_dynamic_tiles": 12,
  "min_dynamic_tiles": 1,
  "mlp_checkpoint": false,
  "mlp_connector_layers": 2,
  "model_type": "eagle_3_vl",
  "output_attentions": false,
  "pad2square": false,
  "pad_token_id": 151643,
  "select_layer": -1,
  "stage": "sft_stage1",
  "template": null,
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "Qwen/Qwen3-1.7B",
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 28,
    "model_type": "qwen3",
    "num_attention_heads": 16,
    "num_hidden_layers": 28,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 151685
  },
  "tie_word_embeddings": true,
  "transformers_version": null,
  "use_backbone_lora": 0,
  "use_cache": false,
  "use_llm_lora": 0,
  "use_pixel_shuffle": true,
  "use_thumbnail": false,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "full_attention_indexes": [
      7,
      14,
      21,
      26
    ],
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip2_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "num_patches": 256,
    "patch_size": 14,
    "use_rope": false,
    "use_windows_attn": false,
    "window_size": 14
  },
  "vocab_size": 151685
}