gliner_config.json

{
  "class_token_index": 128001,
  "decoder_mode": "span",
  "dropout": 0.3,
  "embed_ent_token": true,
  "encoder_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "microsoft/deberta-v3-large",
    "add_cross_attention": false,
    "architectures": null,
    "attention_probs_dropout_prob": 0.1,
    "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,
    "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,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-07,
    "legacy": true,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "max_relative_positions": -1,
    "min_length": 0,
    "model_type": "deberta-v2",
    "no_repeat_ngram_size": 0,
    "norm_rel_ebd": "layer_norm",
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "pooler_dropout": 0,
    "pooler_hidden_act": "gelu",
    "pooler_hidden_size": 1024,
    "pos_att_type": [
      "p2c",
      "c2p"
    ],
    "position_biased_input": false,
    "position_buckets": 256,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "relative_attention": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "share_att_key": true,
    "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,
    "type_vocab_size": 0,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 128003
  },
  "ent_token": "<<ENT>>",
  "eval_every": 10000,
  "fine_tune": true,
  "freeze_token_rep": false,
  "full_decoder_context": true,
  "fuse_layers": false,
  "has_rnn": true,
  "hidden_size": 512,
  "label_smoothing": 0,
  "labels_decoder": "HuggingFaceTB/SmolLM2-135M-Instruct",
  "labels_decoder_config": null,
  "labels_encoder": null,
  "labels_encoder_config": null,
  "log_dir": "models/",
  "loss_alpha": 0.75,
  "loss_gamma": 0,
  "loss_reduction": "mean",
  "lr_encoder": "1e-5",
  "lr_others": "3e-5",
  "max_grad_norm": 10.0,
  "max_len": 512,
  "max_neg_type_ratio": 1,
  "max_types": 30,
  "max_width": 12,
  "model_name": "microsoft/deberta-v3-large",
  "model_type": "gliner",
  "name": "span level gliner",
  "num_post_fusion_layers": 1,
  "num_steps": 500000,
  "post_fusion_schema": null,
  "prev_path": null,
  "random_drop": true,
  "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": 4,
  "train_data": "../data/gliner1M.json",
  "transformers_version": "4.51.0",
  "val_data_dir": "none",
  "vocab_size": 128003,
  "warmup_ratio": 0.05,
  "weight_decay_encoder": 0.01,
  "weight_decay_other": 0.01,
  "words_splitter_type": "whitespace"
}