config.json

{
  "architectures": [
    "SpanMarkerModel"
  ],
  "encoder": {
    "_name_or_path": "studio-ousia/luke-base",
    "add_cross_attention": false,
    "architectures": [
      "LukeForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bert_model_name": "roberta-base",
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "entity_emb_size": 256,
    "entity_vocab_size": 500000,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "id2label": {
      "0": "O",
      "1": "B-PER",
      "2": "I-PER",
      "3": "B-ORG",
      "4": "I-ORG",
      "5": "B-LOC",
      "6": "I-LOC",
      "7": "B-MISC",
      "8": "I-MISC"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "B-LOC": 5,
      "B-MISC": 7,
      "B-ORG": 3,
      "B-PER": 1,
      "I-LOC": 6,
      "I-MISC": 8,
      "I-ORG": 4,
      "I-PER": 2,
      "O": 0
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 514,
    "min_length": 0,
    "model_type": "luke",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "output_scores": false,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "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": "float32",
    "torchscript": false,
    "transformers_version": "4.36.0",
    "type_vocab_size": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "use_entity_aware_attention": true,
    "vocab_size": 50272
  },
  "entity_max_length": 8,
  "id2label": {
    "0": "O",
    "1": "LOC",
    "2": "MISC",
    "3": "ORG",
    "4": "PER"
  },
  "id2reduced_id": {
    "0": 0,
    "1": 4,
    "2": 4,
    "3": 3,
    "4": 3,
    "5": 1,
    "6": 1,
    "7": 2,
    "8": 2
  },
  "label2id": {
    "LOC": 1,
    "MISC": 2,
    "O": 0,
    "ORG": 3,
    "PER": 4
  },
  "marker_max_length": 128,
  "max_next_context": null,
  "max_prev_context": null,
  "model_max_length": null,
  "model_max_length_default": 512,
  "model_type": "span-marker",
  "span_marker_version": "1.5.0",
  "torch_dtype": "float32",
  "trained_with_document_context": false,
  "transformers_version": "4.36.0",
  "vocab_size": 50272
}