{
  "architectures": [
    "UnlimitedOCRForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modeling_unlimitedocr.UnlimitedOCRConfig",
    "AutoModel": "modeling_unlimitedocr.UnlimitedOCRForCausalLM"
  },
  "aux_loss_alpha": 0.001,
  "bos_token_id": 0,
  "candidate_resolutions": [
    [
      1024,
      1024
    ]
  ],
  "dtype": "bfloat16",
  "eos_token_id": 1,
  "ep_size": 1,
  "first_k_dense_replace": 1,
  "global_view_pos": "head",
  "hidden_act": "silu",
  "hidden_size": 1280,
  "initializer_range": 0.02,
  "intermediate_size": 6848,
  "kv_lora_rank": null,
  "language_config": {
    "architectures": [
      "DeepseekOCRForCausalLM"
    ],
    "auto_map": {
      "AutoConfig": "configuration_deepseekv2.DeepseekV2Config",
      "AutoModel": "modeling_deepseek.DeepseekV2Model",
      "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
    },
    "bos_token_id": 0,
    "eos_token_id": 1,
    "first_k_dense_replace": 1,
    "hidden_size": 1280,
    "intermediate_size": 6848,
    "kv_lora_rank": null,
    "lm_head": true,
    "max_position_embeddings": 32768,
    "moe_intermediate_size": 896,
    "n_group": 1,
    "n_routed_experts": 64,
    "n_shared_experts": 2,
    "num_attention_heads": 10,
    "num_experts_per_tok": 6,
    "num_hidden_layers": 12,
    "num_key_value_heads": 10,
    "q_lora_rank": null,
    "qk_nope_head_dim": 0,
    "qk_rope_head_dim": 0,
    "rm_head": false,
    "sliding_window_size": 128,
    "topk_group": 1,
    "topk_method": "greedy",
    "torch_dtype": "bfloat16",
    "use_mla": false,
    "v_head_dim": 128,
    "vocab_size": 129280
  },
  "lm_head": true,
  "max_position_embeddings": 32768,
  "model_type": "unlimited-ocr",
  "moe_intermediate_size": 896,
  "moe_layer_freq": 1,
  "n_group": 1,
  "n_routed_experts": 64,
  "n_shared_experts": 2,
  "norm_topk_prob": false,
  "num_attention_heads": 10,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 12,
  "num_key_value_heads": 10,
  "pretraining_tp": 1,
  "projector_config": {
    "input_dim": 2048,
    "model_type": "mlp_projector",
    "n_embed": 1280,
    "projector_type": "linear"
  },
  "q_lora_rank": null,
  "qk_nope_head_dim": 0,
  "qk_rope_head_dim": 0,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "token",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "channel",
          "symmetric": true,
          "type": "float",
          "zp_dtype": null
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head",
      "re:.*embed_tokens.*",
      "re:.*sam_model.*",
      "re:.*vision_model.*",
      "re:.*projector.*",
      "re:.*mlp\\.gate$",
      "re:.*norm.*"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.16.0"
  },
  "rm_head": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "routed_scaling_factor": 1.0,
  "scoring_func": "softmax",
  "seq_aux": true,
  "sliding_window": 128,
  "sliding_window_size": 128,
  "tie_word_embeddings": false,
  "tile_tag": "2D",
  "topk_group": 1,
  "topk_method": "greedy",
  "transformers_version": "4.57.1",
  "use_cache": true,
  "use_mla": false,
  "v_head_dim": 128,
  "vision_config": {
    "image_size": 1024,
    "mlp_ratio": 3.7362,
    "model_name": "deeplip_b_l",
    "model_type": "vision",
    "width": {
      "clip-l-14-224": {
        "heads": 16,
        "image_size": 224,
        "layers": 24,
        "patch_size": 14,
        "width": 1024
      },
      "sam_vit_b": {
        "downsample_channels": [
          512,
          1024
        ],
        "global_attn_indexes": [
          2,
          5,
          8,
          11
        ],
        "heads": 12,
        "layers": 12,
        "width": 768
      }
    }
  },
  "vocab_size": 129280
}