Upload BioBERT medical classifier

README.md

@@ -0,0 +1,68 @@
+---
+language: en
+license: mit
+tags:
+  - medical
+  - classification
+  - biobert
+  - pubmedqa
+  - healthcare-rag
+datasets:
+  - qiaojin/PubMedQA
+metrics:
+  - f1
+pipeline_tag: text-classification
+---
+
+# BioBERT Medical Query Classifier
+
+Fine-tuned `dmis-lab/biobert-v1.1` for classifying medical questions into 6 categories.
+
+## Categories
+| ID | Category |
+|----|----------|
+| 0 | Diagnosis |
+| 1 | General |
+| 2 | Medication |
+| 3 | Prevention |
+| 4 | Symptoms |
+| 5 | Treatment |
+
+## Results
+| Metric | Score |
+|--------|-------|
+| Macro F1 | 0.9066 |
+| Weighted F1 | 0.9094 |
+| Accuracy | 0.9088 |
+
+## Training Config
+| Item | Value |
+|------|-------|
+| Base model | dmis-lab/biobert-v1.1 |
+| Dataset | qiaojin/PubMedQA (211,186 rows) |
+| Split | 80/10/10 |
+| Epochs | 3 |
+| Learning rate | 2e-5 |
+| Batch size | 16 |
+| Class weights | Balanced (custom WeightedTrainer) |
+
+## Usage
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("AbdoMatrix/biobert-medical-classifier")
+model = AutoModelForSequenceClassification.from_pretrained("AbdoMatrix/biobert-medical-classifier")
+
+text = "What are the symptoms of diabetes?"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+
+predicted = model.config.id2label[torch.argmax(outputs.logits, dim=1).item()]
+print(predicted)  # → Symptoms
+
+## Project
+Healthcare RAG-Powered Medical Q&A Assistant
+eyouth x DEPI | Microsoft Machine Learning Track | 2026
+GitHub: https://github.com/AbdooMatrix/Healthcare-RAG-Powered-Medical-QA-Assistant

config.json

@@ -0,0 +1,45 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Diagnosis",
+    "1": "General",
+    "2": "Medication",
+    "3": "Prevention",
+    "4": "Symptoms",
+    "5": "Treatment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Diagnosis": 0,
+    "General": 1,
+    "Medication": 2,
+    "Prevention": 3,
+    "Symptoms": 4,
+    "Treatment": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c236119e06130ed02a30d63e7f5638dc4898b203fbb3807e0339ee802393e2ba
+size 433283072

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f301ecc0fffa1089253190c30f4fc6c90d1450e2d7d706cc9f9be7d80cc5215d
+size 4856