config.json

{
  "_name_or_path": "./checkpoints/mlcd-embodied-pretrain",
  "add_faster_video": false,
  "add_time_instruction": false,
  "architectures": [
    "LlavaQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "faster_token_stride": 10,
  "force_sample": false,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "anyres",
  "image_crop_resolution": null,
  "image_grid_pinpoints": [
    [
      336,
      336
    ],
    [
      336,
      672
    ],
    [
      336,
      1008
    ],
    [
      336,
      1344
    ],
    [
      336,
      1680
    ],
    [
      336,
      2016
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      672,
      1008
    ],
    [
      672,
      1344
    ],
    [
      672,
      1680
    ],
    [
      1008,
      336
    ],
    [
      1008,
      672
    ],
    [
      1008,
      1008
    ],
    [
      1008,
      1344
    ],
    [
      1008,
      1680
    ],
    [
      1344,
      336
    ],
    [
      1344,
      672
    ],
    [
      1344,
      1008
    ],
    [
      1344,
      1344
    ]
  ],
  "image_split_resolution": null,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_hidden_size": 1024,
  "mm_newline_position": "grid",
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_spatial_pool_mode": "bilinear",
  "mm_spatial_pool_stride": null,
  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "DeepGlint-AI/mlcd-vit-large-patch14-336",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 13768,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "use_mm_proj": true,
  "use_pos_skipping": false,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vocab_size": 152064
}