config.json

{
  "architectures": [
    "LlougatTrainerModel"
  ],
  "decoder": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_implementation": "flash_attention_2",
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "build_bbox_embedding_type": "native",
    "chunk_size_feed_forward": 0,
    "coordinate_retreive_method": "mapping_coordinate_hard",
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": 0,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1",
      "2": "LABEL_2"
    },
    "image_embedding_size": [
      32,
      24
    ],
    "image_size": [
      1024,
      768
    ],
    "init_std": 0.02,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_2": 2
    },
    "length_penalty": 1.0,
    "max_length": 4096,
    "max_position_embeddings": 4096,
    "min_length": 0,
    "mlp_bias": false,
    "model_type": "llougat",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 4,
    "num_key_value_heads": 16,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "position_decoder_decay": 1,
    "prefix": null,
    "pretraining_tp": 1,
    "problem_type": null,
    "prompt_encoder_in_decoder": true,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "unk_token_id": 3,
    "use_bfloat16": false,
    "use_cache": true,
    "use_start_pos_embedding": false,
    "vocab_size": 50232
  },
  "encoder": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "depths": [
      1,
      1,
      9,
      1
    ],
    "dim_embed": [
      128,
      256,
      512,
      1024
    ],
    "diversity_penalty": 0.0,
    "do_sample": false,
    "drop_path_rate": 0.1,
    "early_stopping": false,
    "enable_checkpoint": 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,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_embedding_size": [
      32,
      24
    ],
    "image_feature_source": [
      "spatial_avg_pool",
      "temporal_avg_pool"
    ],
    "image_pos_embed": {
      "max_pos_embeddings": 50,
      "type": "learned_abs_2d"
    },
    "image_size": [
      1024,
      768
    ],
    "input_size": [
      1024,
      768
    ],
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "davit",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_groups": [
      4,
      8,
      16,
      32
    ],
    "num_heads": [
      4,
      8,
      16,
      32
    ],
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_padding": [
      3,
      1,
      1,
      1
    ],
    "patch_prenorm": [
      false,
      true,
      true,
      true
    ],
    "patch_size": [
      7,
      3,
      3,
      3
    ],
    "patch_stride": [
      4,
      2,
      2,
      2
    ],
    "prefix": null,
    "problem_type": null,
    "projection_dim": 768,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_flashattn": true,
    "visual_temporal_embedding": {
      "max_temporal_embeddings": 100,
      "type": "COSINE"
    },
    "window_size": 12
  },
  "is_encoder_decoder": true,
  "model_type": "llougat_ved",
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.42.3"
}