config.json

{
  "architectures": [
    "Qwen2_5_VLForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "vision_start_token_id": 151652,
  "vision_end_token_id": 151653,
  "vision_token_id": 151654,
  "image_token_id": 151655,
  "video_token_id": 151656,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "action_hidden_size": 1024,
  "state_hidden_size": 2024,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 128000,
  "max_window_layers": 70,
  "model_type": "qwen2_5_vl",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": true, 
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "_attn_implementation": "flash_attention_2",
  "use_cache": true,
  "use_sliding_window": false,
  "vision_config": {
    "depth": 32,
    "hidden_act": "silu",
    "hidden_size": 1280,
    "intermediate_size": 3420,
    "num_heads": 16,
    "in_chans": 3,
    "out_hidden_size": 2048,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "window_size": 112,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "tokens_per_second": 2,
    "temporal_patch_size": 2,
    "_attn_implementation": "flash_attention_2"
  },
  "rope_scaling": {
    "type": "mrope",
    "mrope_section": [
      16,
      24,
      24
    ]
  },
  "vocab_size": 151936,
  "num_experts": 2,
  "experts":[
    {
      "hidden_size": 2048,
      "intermediate_size": 11008,
      "hidden_act": "silu"
    },
    {
      "hidden_size": 1024,
      "intermediate_size": 2048,
      "hidden_act": "silu"
    }
  ],
  "dof_config": {
      "follow_left_ee_cartesian_pos": 3,
      "follow_left_ee_rotation": 3,
      "follow_left_gripper": 1,
      "follow_right_ee_cartesian_pos": 3,
      "follow_right_ee_rotation": 3,
      "follow_right_gripper": 1,
      "head_actions": 2,
      "height": 1,
      "velocity_decomposed": 3
  },
  "agent_pos_config": {
      "follow_left_ee_cartesian_pos": 3,
      "follow_left_ee_rotation": 3,
      "follow_left_gripper": 1,
      "follow_right_ee_cartesian_pos": 3,
      "follow_right_ee_rotation": 3,
      "follow_right_gripper": 1,
      "head_actions": 2,
      "height": 1,
      "velocity_decomposed": 3
  },
  "noise_scheduler": {
    "beta_alpha": 1.5,
    "beta_beta": 1.0,
    "s": 0.999,
    "num_inference_timesteps": 10
  },
  "dim_inputs": [2048,1024],
  "attention_moe": true,
  "attention_moe_config":[
    
  ],
  "mlp_moe": true,
  "norm_moe": true,
  "flow_loss_weight": 10.0,
  "causal_action_attention_mask": true
}