Initial commit of the trained NER model with code

config.json

@@ -21,11 +21,91 @@
   "intermediate_size": 2048,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "extended_multitask",
   "num_attention_heads": 8,
   "num_hidden_layers": 8,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "pretrained_config": {
+    "_name_or_path": "dbmdz/bert-medium-historic-multilingual-cased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "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,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "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": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 8,
+    "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": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
   "type_vocab_size": 2,

models.py

@@ -4,6 +4,7 @@ import torch.nn as nn
 from transformers import PreTrainedModel, AutoModel, AutoConfig
 from torch.nn import CrossEntropyLoss
 from typing import Optional, Tuple, Union
+from configuration import ImpressoConfig
 import logging
 
 logger = logging.getLogger(__name__)
@@ -11,7 +12,7 @@ logger = logging.getLogger(__name__)
 
 class ExtendedMultitaskModelForTokenClassification(PreTrainedModel):
 
-    config_class = AutoConfig
+    config_class = ImpressoConfig
     _keys_to_ignore_on_load_missing = [r"position_ids"]
 
     def __init__(self, config, num_token_labels_dict):
@@ -20,7 +21,9 @@ class ExtendedMultitaskModelForTokenClassification(PreTrainedModel):
         self.config = config
 
         # self.bert = AutoModel.from_config(config)
-        self.bert = AutoModel.from_pretrained(config.name_or_path, config=config)
+        self.bert = AutoModel.from_pretrained(
+            config.name_or_path, config=config.pretrained_config
+        )
         if "classifier_dropout" not in config.__dict__:
             classifier_dropout = 0.1
         else: