config.json

{
  "architectures": [
    "LlavaOnevisionForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_llava_onevision.LlavaOnevisionConfig",
    "AutoModel": "modeling_llava_onevision.LlavaOnevisionForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_llava_onevision.LlavaOnevisionForConditionalGeneration",
    "AutoModelForImageTextToText": "modeling_llava_onevision.LlavaOnevisionForConditionalGeneration"
  },
  "hidden_size": 2560,
  "ignore_index": -100,
  "image_grid_pinpoints": [
    [
      384,
      384
    ],
    [
      384,
      768
    ],
    [
      384,
      1152
    ],
    [
      384,
      1536
    ],
    [
      384,
      1920
    ],
    [
      384,
      2304
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      768,
      1152
    ],
    [
      768,
      1536
    ],
    [
      768,
      1920
    ],
    [
      768,
      2304
    ],
    [
      1152,
      384
    ],
    [
      1152,
      768
    ],
    [
      1152,
      1152
    ],
    [
      1152,
      1536
    ],
    [
      1152,
      1920
    ],
    [
      1152,
      2304
    ],
    [
      1536,
      384
    ],
    [
      1536,
      768
    ],
    [
      1536,
      1152
    ],
    [
      1536,
      1536
    ],
    [
      1536,
      1920
    ],
    [
      1536,
      2304
    ],
    [
      1920,
      384
    ],
    [
      1920,
      768
    ],
    [
      1920,
      1152
    ],
    [
      1920,
      1536
    ],
    [
      1920,
      1920
    ],
    [
      1920,
      2304
    ],
    [
      2304,
      384
    ],
    [
      2304,
      768
    ],
    [
      2304,
      1152
    ],
    [
      2304,
      1536
    ],
    [
      2304,
      1920
    ],
    [
      2304,
      2304
    ]
  ],
  "image_token_index": 151655,
  "model_type": "sdar_v",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "/mnt/shared-storage-user/chengshuang/projects/mdllm/llama_factory_sdar/saves/sdar_v_stage1/full/sft",
    "architectures": [
      "SDAR"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
      "AutoConfig": "configuration_sdar.SDARConfig",
      "AutoModel": "modeling_sdar.SDARModel",
      "AutoModelForCausalLM": "modeling_sdar.SDARForCausalLM"
    },
    "block_size": 4,
    "bos_token_id": 151643,
    "debug": false,
    "eos_token_id": 151643,
    "ep_size": 1,
    "fuse_cross_entropy": true,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "mask_token_id": 151669,
    "max_position_embeddings": 32768,
    "max_window_layers": 36,
    "micro_forward": false,
    "model_type": "sdar",
    "num_attention_heads": 32,
    "num_hidden_layers": 36,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "skip_checkpoint": false,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "use_cache": false,
    "use_deepep": false,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.4",
  "use_cache": false,
  "use_image_newline_parameter": true,
  "video_token_index": 151656,
  "vision_aspect_ratio": "anyres_max_9",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "bfloat16",
    "vision_use_head": false
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "full"
}