Upload 19 files

models/biomedical-ner-all/.cache/huggingface/.gitignore

@@ -0,0 +1 @@
+*

models/biomedical-ner-all/.cache/huggingface/download/.gitattributes.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+4a6f8b4e86851998a84353598f557e78c6a947de
+1754896842.240534

models/biomedical-ner-all/.cache/huggingface/download/README.md.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+69f017ddfd0d1d8e218c6dae3be8a5152a240cfd
+1754896842.038518

models/biomedical-ner-all/.cache/huggingface/download/config.json.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+fafdaa630753928d9007e2bc3ee977ac9716f970
+1754896841.0983357

models/biomedical-ner-all/.cache/huggingface/download/model.safetensors.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+d744b846a71ce6ccdb49d7bfe5097eadc41e766ffd28481e1636ed796e820165
+1754896887.3323648

models/biomedical-ner-all/.cache/huggingface/download/pytorch_model.bin.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+b027673a3307002bc2c34795e627691e1a0b906ee3480036fb9a5b06d269f547
+1754896876.2208107

models/biomedical-ner-all/.cache/huggingface/download/special_tokens_map.json.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+a8b3208c2884c4efb86e49300fdd3dc877220cdf
+1754896841.0379386

models/biomedical-ner-all/.cache/huggingface/download/tokenizer.json.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+05a08d51432c8ca05501d170fbc36142a93a163e
+1754896841.1887412

models/biomedical-ner-all/.cache/huggingface/download/tokenizer_config.json.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+732c0433b37b44b3c0b10c740c53ab79d649276e
+1754896841.0983357

models/biomedical-ner-all/.cache/huggingface/download/vocab.txt.metadata

@@ -0,0 +1,3 @@
+015a4050c9ac99722e61c547aa9b4282bcbedc7f
+fb140275c155a9c7c5a3b3e0e77a9e839594a938
+1754896841.3756618

models/biomedical-ner-all/.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

models/biomedical-ner-all/README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- Token Classification
+co2_eq_emissions: 0.0279399890043426
+widget:
+- text: "CASE: A 28-year-old previously healthy man presented with a 6-week history of palpitations.
+The symptoms occurred during rest, 2–3 times per week, lasted up to 30 minutes at a time and were associated with dyspnea.
+Except for a grade 2/6 holosystolic tricuspid regurgitation murmur (best heard at the left sternal border with inspiratory accentuation), physical examination yielded unremarkable findings."
+  example_title: "example 1"
+- text: "A 63-year-old woman with no known cardiac history presented with a sudden onset of dyspnea requiring intubation and ventilatory support out of hospital.
+She denied preceding symptoms of chest discomfort, palpitations, syncope or infection.
+The patient was afebrile and normotensive, with a sinus tachycardia of 140 beats/min."
+  example_title: "example 2"
+- text: "A 48 year-old female presented with vaginal bleeding and abnormal Pap smears.
+Upon diagnosis of invasive non-keratinizing SCC of the cervix, she underwent a radical hysterectomy with salpingo-oophorectomy which demonstrated positive spread to the pelvic lymph nodes and the parametrium.
+Pathological examination revealed that the tumour also extensively involved the lower uterine segment."
+  example_title: "example 3"
+---
+
+## About the Model
+An English Named Entity Recognition model, trained on Maccrobat to recognize the bio-medical entities (107 entities) from a given text corpus (case reports etc.). This model was built on top of distilbert-base-uncased
+
+- Dataset: Maccrobat https://figshare.com/articles/dataset/MACCROBAT2018/9764942
+- Carbon emission: 0.0279399890043426 Kg
+- Training time: 30.16527 minutes
+- GPU used : 1 x GeForce RTX 3060 Laptop GPU
+
+Checkout the tutorial video for explanation of this model and corresponding python library: https://youtu.be/xpiDPdBpS18
+
+## Usage
+The easiest way is to load the inference api from huggingface and second method is through the pipeline object offered by transformers library.
+```python
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
+model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")
+
+pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
+pipe("""The patient reported no recurrence of palpitations at follow-up 6 months after the ablation.""")
+```
+
+## Author
+This model is part of the Research topic "AI in Biomedical field" conducted by Deepak John Reji, Shaina Raza. If you use this work (code, model or dataset), please star at:
+> https://github.com/dreji18/Bio-Epidemiology-NER
+
+## You can support me here :)
+<a href="https://www.buymeacoffee.com/deepakjohnreji" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>

models/biomedical-ner-all/config.json

@@ -0,0 +1,196 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-Activity",
+    "2": "B-Administration",
+    "3": "B-Age",
+    "4": "B-Area",
+    "5": "B-Biological_attribute",
+    "6": "B-Biological_structure",
+    "7": "B-Clinical_event",
+    "8": "B-Color",
+    "9": "B-Coreference",
+    "10": "B-Date",
+    "11": "B-Detailed_description",
+    "12": "B-Diagnostic_procedure",
+    "13": "B-Disease_disorder",
+    "14": "B-Distance",
+    "15": "B-Dosage",
+    "16": "B-Duration",
+    "17": "B-Family_history",
+    "18": "B-Frequency",
+    "19": "B-Height",
+    "20": "B-History",
+    "21": "B-Lab_value",
+    "22": "B-Mass",
+    "23": "B-Medication",
+    "24": "B-Non[biological](Detailed_description",
+    "25": "B-Nonbiological_location",
+    "26": "B-Occupation",
+    "27": "B-Other_entity",
+    "28": "B-Other_event",
+    "29": "B-Outcome",
+    "30": "B-Personal_[back](Biological_structure",
+    "31": "B-Personal_background",
+    "32": "B-Qualitative_concept",
+    "33": "B-Quantitative_concept",
+    "34": "B-Severity",
+    "35": "B-Sex",
+    "36": "B-Shape",
+    "37": "B-Sign_symptom",
+    "38": "B-Subject",
+    "39": "B-Texture",
+    "40": "B-Therapeutic_procedure",
+    "41": "B-Time",
+    "42": "B-Volume",
+    "43": "B-Weight",
+    "44": "I-Activity",
+    "45": "I-Administration",
+    "46": "I-Age",
+    "47": "I-Area",
+    "48": "I-Biological_attribute",
+    "49": "I-Biological_structure",
+    "50": "I-Clinical_event",
+    "51": "I-Color",
+    "52": "I-Coreference",
+    "53": "I-Date",
+    "54": "I-Detailed_description",
+    "55": "I-Diagnostic_procedure",
+    "56": "I-Disease_disorder",
+    "57": "I-Distance",
+    "58": "I-Dosage",
+    "59": "I-Duration",
+    "60": "I-Family_history",
+    "61": "I-Frequency",
+    "62": "I-Height",
+    "63": "I-History",
+    "64": "I-Lab_value",
+    "65": "I-Mass",
+    "66": "I-Medication",
+    "67": "I-Nonbiological_location",
+    "68": "I-Occupation",
+    "69": "I-Other_entity",
+    "70": "I-Other_event",
+    "71": "I-Outcome",
+    "72": "I-Personal_background",
+    "73": "I-Qualitative_concept",
+    "74": "I-Quantitative_concept",
+    "75": "I-Severity",
+    "76": "I-Shape",
+    "77": "I-Sign_symptom",
+    "78": "I-Subject",
+    "79": "I-Texture",
+    "80": "I-Therapeutic_procedure",
+    "81": "I-Time",
+    "82": "I-Volume",
+    "83": "I-Weight"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-Activity": 1,
+    "B-Administration": 2,
+    "B-Age": 3,
+    "B-Area": 4,
+    "B-Biological_attribute": 5,
+    "B-Biological_structure": 6,
+    "B-Clinical_event": 7,
+    "B-Color": 8,
+    "B-Coreference": 9,
+    "B-Date": 10,
+    "B-Detailed_description": 11,
+    "B-Diagnostic_procedure": 12,
+    "B-Disease_disorder": 13,
+    "B-Distance": 14,
+    "B-Dosage": 15,
+    "B-Duration": 16,
+    "B-Family_history": 17,
+    "B-Frequency": 18,
+    "B-Height": 19,
+    "B-History": 20,
+    "B-Lab_value": 21,
+    "B-Mass": 22,
+    "B-Medication": 23,
+    "B-Non[biological](Detailed_description": 24,
+    "B-Nonbiological_location": 25,
+    "B-Occupation": 26,
+    "B-Other_entity": 27,
+    "B-Other_event": 28,
+    "B-Outcome": 29,
+    "B-Personal_[back](Biological_structure": 30,
+    "B-Personal_background": 31,
+    "B-Qualitative_concept": 32,
+    "B-Quantitative_concept": 33,
+    "B-Severity": 34,
+    "B-Sex": 35,
+    "B-Shape": 36,
+    "B-Sign_symptom": 37,
+    "B-Subject": 38,
+    "B-Texture": 39,
+    "B-Therapeutic_procedure": 40,
+    "B-Time": 41,
+    "B-Volume": 42,
+    "B-Weight": 43,
+    "I-Activity": 44,
+    "I-Administration": 45,
+    "I-Age": 46,
+    "I-Area": 47,
+    "I-Biological_attribute": 48,
+    "I-Biological_structure": 49,
+    "I-Clinical_event": 50,
+    "I-Color": 51,
+    "I-Coreference": 52,
+    "I-Date": 53,
+    "I-Detailed_description": 54,
+    "I-Diagnostic_procedure": 55,
+    "I-Disease_disorder": 56,
+    "I-Distance": 57,
+    "I-Dosage": 58,
+    "I-Duration": 59,
+    "I-Family_history": 60,
+    "I-Frequency": 61,
+    "I-Height": 62,
+    "I-History": 63,
+    "I-Lab_value": 64,
+    "I-Mass": 65,
+    "I-Medication": 66,
+    "I-Nonbiological_location": 67,
+    "I-Occupation": 68,
+    "I-Other_entity": 69,
+    "I-Other_event": 70,
+    "I-Outcome": 71,
+    "I-Personal_background": 72,
+    "I-Qualitative_concept": 73,
+    "I-Quantitative_concept": 74,
+    "I-Severity": 75,
+    "I-Shape": 76,
+    "I-Sign_symptom": 77,
+    "I-Subject": 78,
+    "I-Texture": 79,
+    "I-Therapeutic_procedure": 80,
+    "I-Time": 81,
+    "I-Volume": 82,
+    "I-Weight": 83,
+    "O": 0
+  },
+  "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": "4.20.1",
+  "vocab_size": 30522
+}

models/biomedical-ner-all/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d744b846a71ce6ccdb49d7bfe5097eadc41e766ffd28481e1636ed796e820165
+size 265722260

models/biomedical-ner-all/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b027673a3307002bc2c34795e627691e1a0b906ee3480036fb9a5b06d269f547
+size 265743541

models/biomedical-ner-all/special_tokens_map.json

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

models/biomedical-ner-all/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "cuda": 0,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}