{
  "architectures": [
    "PaddleOCRVLForConditionalGeneration"
  ],
  "attention_probs_dropout_prob": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
    "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
  },
  "compression_ratio": 1.0,
  "dtype": "bfloat16",
  "freq_allocation": 20,
  "fuse_ln": false,
  "fuse_rms_norm": true,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1024,
  "ignored_index": -100,
  "image_token_id": 100295,
  "intermediate_size": 3072,
  "max_position_embeddings": 131072,
  "model_type": "paddleocr_vl",
  "num_attention_heads": 16,
  "num_hidden_layers": 18,
  "num_key_value_heads": 2,
  "paddleformers_version": "0.3.2",
  "rms_norm_eps": 1e-05,
  "rope_is_neox_style": true,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 500000,
  "scale_qk_coeff": 1.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "token_balance_seqlen": false,
  "use_3d_rope": true,
  "use_bias": false,
  "use_rmsnorm": true,
  "video_token_id": 101307,
  "vision_config": {
    "_attn_implementation": "eager",
    "_name_or_path": "",
    "_save_to_hf": false,
    "add_cross_attention": false,
    "add_tail_layers": 0,
    "architectures": [
      "SiglipVisionModel"
    ],
    "attention_dropout": 0.0,
    "auto_map": {
      "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
      "AutoModel": "modeling_paddleocr_vl.SiglipVisionModel"
    },
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "context_parallel_degree": 1,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dpo_config": null,
    "dtype": "bfloat16",
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "fuse_attention_ffn": false,
    "fuse_attention_qkv": false,
    "fuse_linear": false,
    "fuse_rope": false,
    "fuse_sequence_parallel_allreduce": false,
    "fuse_swiglu": false,
    "hidden_act": "gelu_new",
    "hidden_size": 1152,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 384,
    "intermediate_size": 4304,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "kto_config": null,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-06,
    "length_penalty": 1.0,
    "loss_subbatch_sequence_length": -1,
    "max_length": 20,
    "min_length": 0,
    "model_type": "paddleocr_vl",
    "moe_subbatch_token_num": 0,
    "no_recompute_layers": null,
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_choices": null,
    "num_hidden_layers": 27,
    "num_return_sequences": 1,
    "offload_recompute_inputs": false,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "patch_size": 14,
    "pipeline_parallel_degree": 1,
    "pp_recompute_interval": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "quantization_config": {
      "act_quant_method": "abs_max",
      "activation_scheme": null,
      "actscale_moving_rate": 0.01,
      "apply_hadamard": false,
      "apply_online_actscale_step": 200,
      "dense_quant_type": "",
      "dtype": null,
      "fmt": null,
      "fp8_format_type": "hybrid",
      "group_size": -1,
      "hadamard_block_size": 32,
      "ignore_modules": null,
      "llm_int8_threshold": 6.0,
      "moe_quant_type": "",
      "qlora_weight_blocksize": 64,
      "qlora_weight_double_quant": false,
      "qlora_weight_double_quant_block_size": 256,
      "quant_input_grad": false,
      "quant_method": null,
      "quant_round_type": 0,
      "quant_type": null,
      "quant_weight_grad": false,
      "quantization": "",
      "scale_epsilon": 1e-08,
      "shift": false,
      "shift_smooth_all_linears": false,
      "smooth": false,
      "weight_block_size": null,
      "weight_quant_method": "abs_max_channel_wise",
      "weight_quantize_algo": null
    },
    "recompute": false,
    "recompute_granularity": "full",
    "recompute_use_reentrant": true,
    "refined_recompute": "",
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": false,
    "return_dict_in_generate": false,
    "sep_parallel_degree": 1,
    "sep_token_id": null,
    "sequence_parallel": false,
    "spatial_merge_size": 2,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "temporal_patch_size": 2,
    "tensor_parallel_degree": 1,
    "tensor_parallel_output": true,
    "tensor_parallel_rank": 0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "tokens_per_second": 2,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "use_cache": false,
    "use_filtered_label_loss": false,
    "use_flash_attention": false,
    "use_fused_dropout_add": false,
    "use_fused_head_and_loss_fn": false,
    "use_fused_linear": false,
    "use_fused_linear_cross_entropy": false,
    "use_fused_rms_norm": false,
    "use_fused_rope": false,
    "use_sparse_head_and_loss_fn": false,
    "virtual_pp_degree": 1
  },
  "vision_start_token_id": 101305,
  "vocab_size": 103424,
  "weight_share_add_bias": true
}