gliner_config.json

{
  "class_token_index": -1,
  "dropout": 0.35,
  "embed_ent_token": true,
  "encoder_config": {
    "_name_or_path": "jhu-clsp/ettin-encoder-400m",
    "add_cross_attention": false,
    "architectures": [
      "ModernBertForMaskedLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 50281,
    "causal_mask": false,
    "chunk_size_feed_forward": 0,
    "classifier_activation": "gelu",
    "classifier_bias": false,
    "classifier_dropout": 0.0,
    "classifier_pooling": "mean",
    "cls_token_id": 50281,
    "cross_attention_hidden_size": null,
    "decoder_bias": true,
    "decoder_start_token_id": null,
    "deterministic_flash_attn": false,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embedding_dropout": 0.0,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 50282,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "global_attn_every_n_layers": 3,
    "global_rope_theta": 160000.0,
    "gradient_checkpointing": false,
    "hidden_activation": "gelu",
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_cutoff_factor": 2.0,
    "initializer_range": 0.02,
    "intermediate_size": 2624,
    "is_causal": false,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "local_attention": 128,
    "local_rope_theta": 160000.0,
    "max_length": 20,
    "max_position_embeddings": 7999,
    "min_length": 0,
    "mlp_bias": false,
    "mlp_dropout": 0.0,
    "model_type": "modernbert",
    "no_repeat_ngram_size": 0,
    "norm_bias": false,
    "norm_eps": 1e-05,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 28,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 50283,
    "position_embedding_type": "sans_pos",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repad_logits_with_grad": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": 50282,
    "sparse_pred_ignore_index": -100,
    "sparse_prediction": false,
    "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,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 50368
  },
  "ent_token": "<<ENT>>",
  "eval_every": 1000,
  "fine_tune": true,
  "focal_loss_prob_margi": 0,
  "freeze_token_rep": false,
  "fuse_layers": false,
  "has_rnn": true,
  "hidden_size": 768,
  "label_smoothing": 0,
  "labels_encoder": "BAAI/bge-base-en-v1.5",
  "labels_encoder_config": {
    "_name_or_path": "BAAI/bge-base-en-v1.5",
    "add_cross_attention": false,
    "architectures": [
      "BertModel"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "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,
    "eos_token_id": null,
    "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": "LABEL_0"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0
    },
    "layer_norm_eps": 1e-12,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "min_length": 0,
    "model_type": "bert",
    "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_scores": false,
    "pad_token_id": 0,
    "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,
    "type_vocab_size": 2,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 30522
  },
  "log_dir": "models/",
  "loss_alpha": 0.7,
  "loss_gamma": 2,
  "loss_reduction": "sum",
  "lr_encoder": "1e-5",
  "lr_others": "3e-5",
  "max_grad_norm": 10.0,
  "max_len": 2048,
  "max_neg_type_ratio": 1,
  "max_types": 100,
  "max_width": 12,
  "model_name": "jhu-clsp/ettin-encoder-400m",
  "model_type": "gliner",
  "name": "span level gliner",
  "num_post_fusion_layers": 1,
  "num_steps": 500000,
  "post_fusion_schema": "",
  "prev_path": null,
  "random_drop": false,
  "root_dir": "gliner_logs",
  "save_total_limit": 3,
  "scheduler_type": "cosine",
  "sep_token": "<<SEP>>",
  "shuffle_types": true,
  "size_sup": -1,
  "span_mode": "markerV0",
  "subtoken_pooling": "first",
  "train_batch_size": 16,
  "train_data": "gliner_fineweb_10M.json",
  "transformers_version": "4.55.0",
  "val_data_dir": "none",
  "vocab_size": -1,
  "warmup_ratio": 0.1,
  "weight_decay_encoder": 0.01,
  "weight_decay_other": 0.01,
  "words_splitter_type": "whitespace"
}