config.json

{
  "architectures": [
    "OpenCUAForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_opencua.OpenCUAConfig",
    "AutoModel": "modeling_opencua.OpenCUAForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_opencua.OpenCUAForConditionalGeneration"
  },
  "ignore_index": -100,
  "media_placeholder_token_id": 151664,
  "model_type": "opencua",
  "pad_token_id": 0,
  "text_config": {
    "bos_token_id": 151643,
    "eos_token_id": 151644,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "k_proj_bias": true,
    "max_length": 20,
    "min_length": 0,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "pad_token_id": 152063,
    "pretraining_sequence_length": 128000,
    "q_proj_bias": true,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "use_bfloat16": false,
    "use_cache": true,
    "v_proj_bias": true,
    "vocab_size": 152064
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.3",
  "vision_config": {
    "depth": 32,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "hidden_act": "silu",
    "hidden_size": 1280,
    "num_heads": 16,
    "in_chans": 3,
    "intermediate_size": 3420,
    
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "temporal_patch_size": 2,
    "out_hidden_size": 3584,
    "tokens_per_second": 2,
    "window_size": 112
  },
  "vocab_size": 152064
}