Upload 8 files

This model is a high-performance named entity recognition (NER) model achieving an overall F1-score of 0.97. It is optimized for identifying medical entities such as diseases, symptoms, procedures, and provider types, with strong precision and recall across diverse entity types, making it ideal for healthcare text processing tasks.

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "B-DISEASE",
+    "1": "B-DOCUMENT_TYPE",
+    "2": "B-DOS",
+    "3": "B-DOS_A",
+    "4": "B-DOS_D",
+    "5": "B-LAB",
+    "6": "B-MEDICINE",
+    "7": "B-PROCEDURE",
+    "8": "B-PROVIDER_INDIVIDUAL",
+    "9": "B-PROVIDER_ORG",
+    "10": "B-SECTION_HEADING",
+    "11": "B-SYMPTOM",
+    "12": "B-VISIT_TYPE",
+    "13": "I-DISEASE",
+    "14": "I-DOCUMENT_TYPE",
+    "15": "I-DOS",
+    "16": "I-DOS_A",
+    "17": "I-DOS_D",
+    "18": "I-LAB",
+    "19": "I-MEDICINE",
+    "20": "I-PROCEDURE",
+    "21": "I-PROVIDER_INDIVIDUAL",
+    "22": "I-PROVIDER_ORG",
+    "23": "I-SECTION_HEADING",
+    "24": "I-SYMPTOM",
+    "25": "I-VISIT_TYPE",
+    "26": "O"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-DISEASE": 0,
+    "B-DOCUMENT_TYPE": 1,
+    "B-DOS": 2,
+    "B-DOS_A": 3,
+    "B-DOS_D": 4,
+    "B-LAB": 5,
+    "B-MEDICINE": 6,
+    "B-PROCEDURE": 7,
+    "B-PROVIDER_INDIVIDUAL": 8,
+    "B-PROVIDER_ORG": 9,
+    "B-SECTION_HEADING": 10,
+    "B-SYMPTOM": 11,
+    "B-VISIT_TYPE": 12,
+    "I-DISEASE": 13,
+    "I-DOCUMENT_TYPE": 14,
+    "I-DOS": 15,
+    "I-DOS_A": 16,
+    "I-DOS_D": 17,
+    "I-LAB": 18,
+    "I-MEDICINE": 19,
+    "I-PROCEDURE": 20,
+    "I-PROVIDER_INDIVIDUAL": 21,
+    "I-PROVIDER_ORG": 22,
+    "I-SECTION_HEADING": 23,
+    "I-SYMPTOM": 24,
+    "I-VISIT_TYPE": 25,
+    "O": 26
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:925cdb6b84985b8176010ee8912b923b5d0e97f1322ec4a7ab033574e8062766
+size 871329797

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02898b0130d0cd667f80eebe553712c895afdfa27f8641d6c7ea3adea25cf24f
+size 265569890

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b53a607245efc9146dd4ce91edbbd4f1bf7feeb8310d04d3a25343834daedd
+size 4024