File upload

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "classla/bcms-bertic",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-COM",
+    "1": "I-COM",
+    "2": "B-ADR",
+    "3": "I-ADR",
+    "4": "O",
+    "5": "B-REF",
+    "6": "B-LAW",
+    "7": "I-LAW",
+    "8": "B-PER",
+    "9": "I-PER",
+    "10": "B-TOP",
+    "11": "I-TOP",
+    "12": "I-REF",
+    "13": "B-MONEY",
+    "14": "I-MONEY",
+    "15": "B-DATE",
+    "16": "I-DATE",
+    "17": "B-INST",
+    "18": "I-INST",
+    "19": "B-IDCOM",
+    "20": "B-IDOTH",
+    "21": "B-NUMDOC",
+    "22": "B-MISC",
+    "23": "I-MISC",
+    "24": "B-CONTACT",
+    "25": "B-IDPER",
+    "26": "B-NUMPLOT",
+    "27": "B-IDTAX",
+    "28": "B-COURT",
+    "29": "I-COURT",
+    "30": "B-NUMCAR",
+    "31": "B-ORGOTH",
+    "32": "I-ORGOTH",
+    "33": "I-NUMCAR",
+    "34": "B-NUMACC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADR": 2,
+    "B-COM": 0,
+    "B-CONTACT": 24,
+    "B-COURT": 28,
+    "B-DATE": 15,
+    "B-IDCOM": 19,
+    "B-IDOTH": 20,
+    "B-IDPER": 25,
+    "B-IDTAX": 27,
+    "B-INST": 17,
+    "B-LAW": 6,
+    "B-MISC": 22,
+    "B-MONEY": 13,
+    "B-NUMACC": 34,
+    "B-NUMCAR": 30,
+    "B-NUMDOC": 21,
+    "B-NUMPLOT": 26,
+    "B-ORGOTH": 31,
+    "B-PER": 8,
+    "B-REF": 5,
+    "B-TOP": 10,
+    "I-ADR": 3,
+    "I-COM": 1,
+    "I-COURT": 29,
+    "I-DATE": 16,
+    "I-INST": 18,
+    "I-LAW": 7,
+    "I-MISC": 23,
+    "I-MONEY": 14,
+    "I-NUMCAR": 33,
+    "I-ORGOTH": 32,
+    "I-PER": 9,
+    "I-REF": 12,
+    "I-TOP": 11,
+    "O": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 100, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 64, "max_grad_norm": 1.0, "max_seq_length": 512, "model_name": "classla/bcms-bertic", "model_type": "electra", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": true, "no_save": false, "not_saved_args": [], "num_train_epochs": 20, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 14, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": true, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 8, "train_custom_parameters_only": false, "trust_remote_code": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 716, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["B-COM", "I-COM", "B-ADR", "I-ADR", "O", "B-REF", "B-LAW", "I-LAW", "B-PER", "I-PER", "B-TOP", "I-TOP", "I-REF", "B-MONEY", "I-MONEY", "B-DATE", "I-DATE", "B-INST", "I-INST", "B-IDCOM", "B-IDOTH", "B-NUMDOC", "B-MISC", "I-MISC", "B-CONTACT", "B-IDPER", "B-NUMPLOT", "B-IDTAX", "B-COURT", "I-COURT", "B-NUMCAR", "B-ORGOTH", "I-ORGOTH", "I-NUMCAR", "B-NUMACC"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}