Cardiology embedding model (separation: 0.386)

README.md

@@ -0,0 +1,55 @@
+---
+library_name: peft
+base_model: sentence-transformers/all-mpnet-base-v2
+tags:
+- medical
+- cardiology
+- embeddings
+- domain-adaptation
+- lora
+- sentence-transformers
+- sentence-similarity
+language:
+- en
+license: apache-2.0
+---
+
+# CardioEmbed-MPNet-base
+
+**Domain-specialized cardiology text embeddings using LoRA-adapted MPNet-base**
+
+Part of a comparative study of 10 embedding architectures for clinical cardiology.
+
+## Performance
+
+| Metric | Score |
+|--------|-------|
+| Separation Score | **0.386** |
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoTokenizer
+from peft import PeftModel
+
+base_model = AutoModel.from_pretrained("sentence-transformers/all-mpnet-base-v2")
+tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2")
+model = PeftModel.from_pretrained(base_model, "richardyoung/CardioEmbed-MPNet-base")
+```
+
+## Training
+
+- **Training Data**: 106,535 cardiology text pairs from medical textbooks
+- **Method**: LoRA fine-tuning (r=16, alpha=32)
+- **Loss**: Multiple Negatives Ranking Loss (InfoNCE)
+
+## Citation
+
+```bibtex
+@article{young2024comparative,
+  title={Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation},
+  author={Young, Richard J and Matthews, Alice M},
+  journal={arXiv preprint},
+  year={2024}
+}
+```

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "sentence-transformers/all-mpnet-base-v2",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "k",
+    "v"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e57ad9066d90adbb68c5825309a133eebbe50b8a61bd8acf53c7be187cd4fb
+size 3548456

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MPNetTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_config.json

@@ -0,0 +1,18 @@
+{
+  "name": "all-mpnet-base-v2",
+  "model_id": "sentence-transformers/all-mpnet-base-v2",
+  "batch_size": 48,
+  "gradient_accumulation_steps": 1,
+  "learning_rate": 2e-05,
+  "epochs": 3,
+  "max_seq_length": 512,
+  "lora_r": 16,
+  "lora_alpha": 32,
+  "use_8bit": false,
+  "target_modules": [
+    "q",
+    "k",
+    "v"
+  ],
+  "output_dir": "mpnet_base_cardiology"
+}