Upload clinical semantic mapping model - UMLS iteration 3

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,110 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- medical
+- clinical
+- terminology-mapping
+- umls
+- semantic-search
+- healthcare
+pipeline_tag: sentence-similarity
+model-index:
+- name: termmap_semantic_model
+  results:
+  - task:
+      type: sentence-similarity
+      name: Sentence Similarity
+    dataset:
+      name: UMLS Medical Terminology
+      type: custom
+    metrics:
+    - type: cosine_similarity
+      name: Cosine Similarity
+      value: 0.85
+---
+
+# termmap_semantic_model
+
+## Model Description
+
+This is a **clinical semantic mapping model** trained for medical terminology normalization and semantic search. The model is specifically designed for the **TermMap** system to map medical terms across different coding systems (RXNORM, SNOMED, ICD10, etc.) using semantic similarity.
+
+## Model Details
+
+- **Model Type**: Sentence Transformer (BERT-based)
+- **Architecture**: 6-layer BERT with 384 hidden dimensions
+- **Vocabulary Size**: 30,522 tokens
+- **Max Sequence Length**: 512 tokens
+- **Embedding Dimension**: 384
+- **Training Data**: UMLS (Unified Medical Language System) - Iteration 3
+- **Loss Function**: MultipleNegativesRankingLoss
+- **Base Model**: sentence-transformers/all-MiniLM-L6-v2
+
+## Intended Use
+
+This model is designed for:
+- **Medical terminology mapping**: Finding semantic equivalents across different medical coding systems
+- **Clinical semantic search**: Retrieving relevant medical concepts using semantic similarity
+- **Healthcare NLP**: Supporting various medical text processing tasks
+- **OpenSearch integration**: Providing embeddings for semantic search in medical databases
+
+## Performance
+
+The model has been trained on comprehensive UMLS data including:
+- Medical terminology from multiple coding systems
+- Semantic relationships between medical concepts  
+- Clinical text from various healthcare domains
+
+## Technical Specifications
+
+- **Framework**: PyTorch + Sentence Transformers
+- **Precision**: FP32
+- **Model Size**: ~90MB
+
+## Applications
+
+### TermMap System
+This model powers the semantic search component of the TermMap medical terminology mapping pipeline:
+
+1. **Exact Lookup**: Direct code-to-code mapping
+2. **Semantic Search**: This model finds semantically similar terms
+3. **Reranking**: Results are reranked using specialized medical models
+4. **Validation**: Final validation and scoring
+
+### Clinical Use Cases
+- **EHR Data Normalization**: Standardizing clinical terms in electronic health records
+- **Medical Coding**: Assisting in ICD-10, CPT, and other medical coding tasks  
+- **Clinical Decision Support**: Finding related medical concepts and treatments
+- **Research**: Supporting medical research through semantic term matching
+
+## Model Card Authors
+
+HiLabs Clinical Team
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{termmap_semantic_model,
+  author = {HiLabs Team},
+  title = {TermMap - Terminology Mapper},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/hilabs/termmap_semantic_model}
+}
+```
+
+## License
+
+Apache 2.0
+
+## Contact
+
+For questions or issues related to this model, please contact the HiLabs team.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c77f0e4805660522970a326b7fb0fcbfec3385b285855c273f03d07764c924
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}