Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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
+}

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef5fea9d0f2a2059b0914004aa94a87dfa48772c6922d7d33dcefc01dae2d00
+size 9437272

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff5c695c0ed04480a9ea2e378e6b5a583420aa3419ffeb159f615d35bca3065
+size 9437272

README.md

@@ -0,0 +1,639 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:1340
+- loss:TripletLoss
+base_model: unsloth/embeddinggemma-300m
+widget:
+- source_sentence: How many 'Laboratory' sub-type admissions from the last year have
+    not yet generated an invoice, and what is the average duration (in days) from
+    their admission date to today?
+  sentences:
+  - 'Primary reference table listing the most granular level of administrative geography,
+    typically representing villages or ''kelurahan''. It provides standardized names
+    and codes for these local areas, linking each sub-district to its parent `DistrictId`
+    to complete the geographic hierarchy. **Use this table to** perform highly localized
+    demographic analysis, standardize patient addresses to the village level, or define
+    precise service areas. **Note: This is a static lookup list of geographic areas
+    and does not contain any patient-specific addresses, postal codes, or household
+    information.**'
+  - 'Primary reference table defining the lifecycle stages of a patient admission
+    event. It categorizes visits into states such as ''Active'' (currently in hospital),
+    ''Discharged'' (left hospital), ''Invoiced'' (bill generated), or ''Cancelled''.
+    Use this table to interpret AdmissionStatusId in transaction tables to filter
+    visits by their current operational state (e.g., calculating current census vs.
+    historical discharges). Note: This is a static lookup table for status definitions,
+    NOT a transaction log of patient movements.'
+  - 'Operational transaction table (Financial Log) recording the header-level details
+    of patient invoices and billing events. This table captures the financial breakdown
+    of a visit, distinguishing between Patient responsibility (Out-of-pocket) and
+    Payer responsibility (Insurance/Corporate Coverage), including Gross Amounts,
+    Discounts, Taxes, and Net Payable values. Use this table to analyze hospital revenue
+    streams, track Accounts Receivable (AR), monitor billing cancellations, or calculate
+    the financial yield per admission. Note: This is the Invoice HEADER table containing
+    total values; it does not typically list the specific individual line items (drugs,
+    labs, services) charged within the bill. For any financial analysis related to
+    hospital revenue, Payments, Accounts Receivable (AR), billing breakdowns, or insurance
+    claims, this invoice header table is the definitive starting point.'
+- source_sentence: Calculate the proportion of invoices issued to patients with 'Inactive'
+    medical records out of the total invoices issued in the last fiscal year.
+  sentences:
+  - 'Standard reference table for patient biological sex and gender classification.
+    Contains standard values ''Male'' (Pria) and ''Female'' (Wanita). Use this table
+    to filter patient demographics by gender, support clinical reference range checks,
+    or generate gender-based population statistics. Note: Used for biological sex
+    classification.'
+  - 'Primary reference table storing the comprehensive master profiles of all patients
+    registered in the hospital system. It contains critical demographic data including
+    Name, Medical Record Number (MrNo), Birth Date, Gender (SexId), Address, Contact
+    Information (Phone, Email), and Identification details (National ID, Passport).
+    It also tracks patient status (Active/Merged/Deceased) and links to external Payer/Insurance
+    information. Use this table to identify unique patients, retrieve contact details
+    for notifications, segment patient populations by demographics, or link clinical
+    transactions to specific individuals. Note: This table represents the ''Golden
+    Record'' of a patient''s identity; historical changes might be tracked in audit
+    logs, but this table holds the current state.'
+  - 'Primary reference table storing the comprehensive master profiles of all patients
+    registered in the hospital system. It contains critical demographic data including
+    Name, Medical Record Number (MrNo), Birth Date, Gender (SexId), Address, Contact
+    Information (Phone, Email), and Identification details (National ID, Passport).
+    It also tracks patient status (Active/Merged/Deceased) and links to external Payer/Insurance
+    information. Use this table to identify unique patients, retrieve contact details
+    for notifications, segment patient populations by demographics, or link clinical
+    transactions to specific individuals. Note: This table represents the ''Golden
+    Record'' of a patient''s identity; historical changes might be tracked in audit
+    logs, but this table holds the current state.'
+- source_sentence: What is the total number of invoices and the total value of these
+    invoices issued in Q1 2024 for female patients whose current status is 'Active'?
+  sentences:
+  - 'Operational snapshot table that holds the **single, current financial state**
+    of a patient at a specific hospital unit. Unlike a transaction log, this table
+    does not track history; it contains only the final calculated totals: `BalanceAmount`
+    (Total AR/Debt outstanding) and `DepositBalanceAmount` (Total Advance Payment
+    available). **Use this table for** quick validation of whether a patient can be
+    discharged, checking total debt before billing, or viewing available deposit funds.
+    **Concept:** Think of this as the ''ATM Screen Balance'' showing only the final
+    amount available right now.'
+  - 'Primary reference table defining the validity and lifecycle status of a patient''s
+    master record. Contains status codes such as ''Active'', ''Inactive'', and ''Deceased''
+    to classify patient accounts. **Use this table to** look up status meanings or
+    filter patient queries based on their account state (e.g., excluding deceased
+    patients from active lists). **Note: This is a lookup dictionary for status codes,
+    NOT a transaction log of status changes for specific patients.**'
+  - 'Operational transaction table recording individual line items within patient
+    invoices (Accounts Receivable). It captures granular billing details including
+    specific items sold (drugs, services), quantities, unit prices, discounts, tax
+    calculations, and the financial split between Patient and Payer (Insurance/Guarantor).
+    It also tracks revenue allocation (Hospital vs. Doctor portion). **Use this table
+    to** generate detailed patient bills, audit revenue streams per item, calculate
+    doctor performance fees, or analyze discount utilization. **Note: This table contains
+    financial billing data per item, NOT the clinical medical results or the master
+    list of available services.**'
+- source_sentence: How many unique male patients were referred by a 'Doctor Referral'
+    and had a 'General' patient type for any admission in the last 6 months?
+  sentences:
+  - 'Operational transaction table (Financial Log) recording the header-level details
+    of patient invoices and billing events. This table captures the financial breakdown
+    of a visit, distinguishing between Patient responsibility (Out-of-pocket) and
+    Payer responsibility (Insurance/Corporate Coverage), including Gross Amounts,
+    Discounts, Taxes, and Net Payable values. Use this table to analyze hospital revenue
+    streams, track Accounts Receivable (AR), monitor billing cancellations, or calculate
+    the financial yield per admission. Note: This is the Invoice HEADER table containing
+    total values; it does not typically list the specific individual line items (drugs,
+    labs, services) charged within the bill. For any financial analysis related to
+    hospital revenue, Payments, Accounts Receivable (AR), billing breakdowns, or insurance
+    claims, this invoice header table is the definitive starting point.'
+  - 'Standard reference table for patient biological sex and gender classification.
+    Contains standard values ''Male'' (Pria) and ''Female'' (Wanita). Use this table
+    to filter patient demographics by gender, support clinical reference range checks,
+    or generate gender-based population statistics. Note: Used for biological sex
+    classification.'
+  - 'Operational transaction table recording unstructured free-text medical notes
+    and preliminary clinical remarks associated with a patient admission. It captures
+    initial diagnosis impressions, symptoms, or observation notes (e.g., ''Asthma'',
+    ''Observation Febris'') entered during the admission process. Use this table to
+    retrieve qualitative clinical context for a visit or search for specific medical
+    conditions mentioned in preliminary notes. Note: This table contains raw free-text
+    descriptions, NOT structured ICD-10 diagnosis codes used for billing.'
+- source_sentence: Retrieve the names of all patients who have a 'MedicalRecordStatusId'
+    indicating 'Active' in their PatientOrganization record and have received an invoice
+    from any organization in the current month.
+  sentences:
+  - 'Primary reference table storing the comprehensive master profiles of all patients
+    registered in the hospital system. It contains critical demographic data including
+    Name, Medical Record Number (MrNo), Birth Date, Gender (SexId), Address, Contact
+    Information (Phone, Email), and Identification details (National ID, Passport).
+    It also tracks patient status (Active/Merged/Deceased) and links to external Payer/Insurance
+    information. Use this table to identify unique patients, retrieve contact details
+    for notifications, segment patient populations by demographics, or link clinical
+    transactions to specific individuals. Note: This table represents the ''Golden
+    Record'' of a patient''s identity; historical changes might be tracked in audit
+    logs, but this table holds the current state.'
+  - 'Primary reference table defining the standard set of religions and spiritual
+    beliefs for patient demographic data. It contains codes and names for major religions
+    such as Islam, Christian, Catholic, Hindu, and Buddhist. **Use this table to**
+    interpret the `ReligionId` from patient master data to standardize demographic
+    reporting or analyze patient spiritual care needs. **Note: This table lists the
+    CATEGORIES of religion only, not the religious affiliation of individual patients.**'
+  - 'Operational transaction table (Financial Log) recording the header-level details
+    of patient invoices and billing events. This table captures the financial breakdown
+    of a visit, distinguishing between Patient responsibility (Out-of-pocket) and
+    Payer responsibility (Insurance/Corporate Coverage), including Gross Amounts,
+    Discounts, Taxes, and Net Payable values. Use this table to analyze hospital revenue
+    streams, track Accounts Receivable (AR), monitor billing cancellations, or calculate
+    the financial yield per admission. Note: This is the Invoice HEADER table containing
+    total values; it does not typically list the specific individual line items (drugs,
+    labs, services) charged within the bill. For any financial analysis related to
+    hospital revenue, Payments, Accounts Receivable (AR), billing breakdowns, or insurance
+    claims, this invoice header table is the definitive starting point.'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on unsloth/embeddinggemma-300m
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.03283582089552239
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.0626865671641791
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.08358208955223881
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.13134328358208955
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.03283582089552239
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.0208955223880597
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.01671641791044776
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.013134328358208956
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.03283582089552239
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.0626865671641791
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.08358208955223881
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.13134328358208955
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.07347950410091954
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.05603056147832267
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.06301005721428388
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on unsloth/embeddinggemma-300m
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [unsloth/embeddinggemma-300m](https://huggingface.co/unsloth/embeddinggemma-300m). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [unsloth/embeddinggemma-300m](https://huggingface.co/unsloth/embeddinggemma-300m) <!-- at revision bfa3c846ac738e62aa61806ef9112d34acb1dc5a -->
+- **Maximum Sequence Length:** 768 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 768, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (1): Pooling({'word_embedding_dimension': 768, '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})
+  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (4): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("afalaudn/gemma-embedding-ft3")
+# Run inference
+sentences = [
+    "Retrieve the names of all patients who have a 'MedicalRecordStatusId' indicating 'Active' in their PatientOrganization record and have received an invoice from any organization in the current month.",
+    "Primary reference table storing the comprehensive master profiles of all patients registered in the hospital system. It contains critical demographic data including Name, Medical Record Number (MrNo), Birth Date, Gender (SexId), Address, Contact Information (Phone, Email), and Identification details (National ID, Passport). It also tracks patient status (Active/Merged/Deceased) and links to external Payer/Insurance information. Use this table to identify unique patients, retrieve contact details for notifications, segment patient populations by demographics, or link clinical transactions to specific individuals. Note: This table represents the 'Golden Record' of a patient's identity; historical changes might be tracked in audit logs, but this table holds the current state.",
+    'Primary reference table defining the standard set of religions and spiritual beliefs for patient demographic data. It contains codes and names for major religions such as Islam, Christian, Catholic, Hindu, and Buddhist. **Use this table to** interpret the `ReligionId` from patient master data to standardize demographic reporting or analyze patient spiritual care needs. **Note: This table lists the CATEGORIES of religion only, not the religious affiliation of individual patients.**',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000,  0.6662, -0.1269],
+#         [ 0.6662,  1.0000,  0.1456],
+#         [-0.1269,  0.1456,  1.0000]])
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.0328     |
+| cosine_accuracy@3   | 0.0627     |
+| cosine_accuracy@5   | 0.0836     |
+| cosine_accuracy@10  | 0.1313     |
+| cosine_precision@1  | 0.0328     |
+| cosine_precision@3  | 0.0209     |
+| cosine_precision@5  | 0.0167     |
+| cosine_precision@10 | 0.0131     |
+| cosine_recall@1     | 0.0328     |
+| cosine_recall@3     | 0.0627     |
+| cosine_recall@5     | 0.0836     |
+| cosine_recall@10    | 0.1313     |
+| **cosine_ndcg@10**  | **0.0735** |
+| cosine_mrr@10       | 0.056      |
+| cosine_map@100      | 0.063      |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 1,340 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                             | negative                                                                             |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               | string                                                                               |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 35.94 tokens</li><li>max: 82 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 129.79 tokens</li><li>max: 171 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 112.02 tokens</li><li>max: 175 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                      | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What is the total number of patient admissions that resulted in a 'Recovered' discharge condition for each organization in 2023?</code>                                                                                               | <code>Operational transaction table recording every patient registration and visit event at the hospital. This table consolidates patient demographics, visit types (Inpatient, Outpatient, Emergency), primary and referral doctors, payer/insurance eligibility, and critical timelines (Admission and Discharge dates). Use this table to calculate patient census, Average Length of Stay (ALOS), track patient flow, or analyze admission volume by doctor or department. Note: This table focuses on administrative registration and billing initiation; it does not contain detailed clinical notes, specific lab results, or medication prescriptions. When analyzing patient administrative inflow and outflow data, this table is the primary and essential source for all patient visit metrics.</code>                                                                                                                         | <code>This reference table defines the high-level administrative outcomes of a patient's discharge process. It includes standard codes, English names, and Indonesian translations (LocalName) such as 'Discharged' (Pulang) and 'Cancelled' (Batal). Use this table to categorize the final resolution of a hospital visit, determining if a patient successfully left care or if the discharge process was voided. Note: This table tracks the administrative status of the discharge event itself, not the clinical medical condition (e.g., improved, cured) or the specific reason for discharge.</code>                                                                                                             |
+  | <code>Retrieve the AdmissionNo and InvoiceNo for all admissions where the patient was not previously registered (Admission.IsPatientRegistered = 0) and the invoice was issued by an organization with an IsActive status of 'true'.</code> | <code>Operational transaction table (Financial Log) recording the header-level details of patient invoices and billing events. This table captures the financial breakdown of a visit, distinguishing between Patient responsibility (Out-of-pocket) and Payer responsibility (Insurance/Corporate Coverage), including Gross Amounts, Discounts, Taxes, and Net Payable values. Use this table to analyze hospital revenue streams, track Accounts Receivable (AR), monitor billing cancellations, or calculate the financial yield per admission. Note: This is the Invoice HEADER table containing total values; it does not typically list the specific individual line items (drugs, labs, services) charged within the bill. For any financial analysis related to hospital revenue, Payments, Accounts Receivable (AR), billing breakdowns, or insurance claims, this invoice header table is the definitive starting point.</code> | <code>Operational transaction table recording formal requests to retrieve physical medical record folders from the Medical Records Department (MRD). It tracks the details of the request, including the specific patient file (`PatientOrganizationId`), the requesting doctor (`DoctorUserId`), the intended destination (`FolderDestinationTypeId`), and the urgency or type of request (`FolderRequestTypeId`). **Use this table to** measure MRD service levels, track the volume of physical file retrievals, or audit the reasons for accessing physical records. **Note: This tracks the *request* for a physical object, NOT the digital access to the EMR or the actual content of the medical record.**</code> |
+  | <code>What is the average age of patients with 'Active' status who had an 'Inpatient' admission in 2024, compared to those with 'Inactive' status?</code>                                                                                   | <code>Operational transaction table recording every patient registration and visit event at the hospital. This table consolidates patient demographics, visit types (Inpatient, Outpatient, Emergency), primary and referral doctors, payer/insurance eligibility, and critical timelines (Admission and Discharge dates). Use this table to calculate patient census, Average Length of Stay (ALOS), track patient flow, or analyze admission volume by doctor or department. Note: This table focuses on administrative registration and billing initiation; it does not contain detailed clinical notes, specific lab results, or medication prescriptions. When analyzing patient administrative inflow and outflow data, this table is the primary and essential source for all patient visit metrics.</code>                                                                                                                         | <code>Operational transaction table recording the official event of a patient leaving the hospital (Discharge). It captures the precise discharge timestamp, the patient's condition upon exit (e.g., Recovered, Improved), and the type of discharge (e.g., Medical Consent, Transfer) linked to their Admission. **Use this table to** calculate Length of Stay (LOS), analyze clinical outcomes, or track bed turnover rates. **Note: This table signifies the physical or administrative end of a visit; it does NOT contain the final invoice amount, though it triggers the billing closure process.**</code>                                                                                                       |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.COSINE",
+      "triplet_margin": 1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 335 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 335 samples:
+  |         | anchor                                                                             | positive                                                                             | negative                                                                             |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               | string                                                                               |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 35.25 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 128.23 tokens</li><li>max: 171 tokens</li></ul> | <ul><li>min: 63 tokens</li><li>mean: 111.21 tokens</li><li>max: 171 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                              | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Retrieve the admission number, invoice number, and admission type name for all admissions that occurred in January 2023 and had an invoice issued within 7 days of the admission date.</code> | <code>Primary reference table defining the high-level classification of patient visits and hospital service lines. Contains standard categories including Inpatient (Hospitalization), Outpatient (Clinical visits), Emergency (ER), and Health Checkups (MCU). Use this table to group patient volume by service type, filter admission logs, or analyze revenue streams by visit category. Note: This is a static lookup list defining the 'Types' of visits; it does not contain actual patient visit transaction records.</code>                                                                                                         | <code>Operational transaction table that records the detailed line items of an inventory stock take event. It captures the specific `ItemId` being counted, the quantity recorded in the system (`SystemStockQuantity`), the actual `PhysicalStockQuantity` counted, and the resulting `VarianceStockQuantity`. For batch-tracked items, it also includes `BatchNo` and `ExpiryDate`. **Use this table to** analyze inventory discrepancies, identify expired or expiring stock during a count, or audit the accuracy of stock records for a specific item. **Note: This table contains the detailed results of a specific stock count *event*; it does NOT provide the real-time inventory balance of an item.**</code> |
+  | <code>What is the total number of invoices and the total value of these invoices issued in Q1 2024 for female patients whose current status is 'Active'?</code>                                     | <code>Primary reference table defining the validity and lifecycle status of a patient's master record. Contains status codes such as 'Active', 'Inactive', and 'Deceased' to classify patient accounts. **Use this table to** look up status meanings or filter patient queries based on their account state (e.g., excluding deceased patients from active lists). **Note: This is a lookup dictionary for status codes, NOT a transaction log of status changes for specific patients.**</code>                                                                                                                                            | <code>Operational snapshot table that holds the **single, current financial state** of a patient at a specific hospital unit. Unlike a transaction log, this table does not track history; it contains only the final calculated totals: `BalanceAmount` (Total AR/Debt outstanding) and `DepositBalanceAmount` (Total Advance Payment available). **Use this table for** quick validation of whether a patient can be discharged, checking total debt before billing, or viewing available deposit funds. **Concept:** Think of this as the 'ATM Screen Balance' showing only the final amount available right now.</code>                                                                                              |
+  | <code>Tampilkan data Master Data Hospital Rooms (Room)</code>                                                                                                                                       | <code>Primary reference table defining individual patient rooms within a hospital ward. It contains specific room codes and names, linking each room to its parent Ward (`WardId`) and hospital branch (`OrganizationId`), representing the most granular level of inpatient location master data. **Use this table to** map `RoomId` from bed management or admission transactions to a specific room number, analyze room availability, or manage hospital accommodation resources. **Note: This table lists the physical room definitions only, not the individual beds within a room or the real-time patient occupancy status.**</code> | <code>Operational transaction table recording the historical log of bed movements and transfers within the hospital organization. This table captures the exact timestamp of transfer events and identifies the specific Bed asset involved. Use this table to track the history of bed locations, audit bed usage timelines, or monitor the frequency of bed transfers. Note: This table focuses on the physical Bed entity's movement timeline; based on the provided columns, it does not explicitly contain Patient or Admission IDs.</code>                                                                                                                                                                         |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.COSINE",
+      "triplet_margin": 1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `prompts`: {'anchor': ' ', 'positive': '', 'negative': ''}
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: {'anchor': ' ', 'positive': '', 'negative': ''}
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:--------------:|
+| -1     | -1   | -             | -               | 0.0698         |
+| 0.2381 | 5    | 0.7215        | 0.3602          | 0.0706         |
+| 0.4762 | 10   | 0.3287        | 0.2451          | 0.0765         |
+| 0.7143 | 15   | 0.2145        | 0.1896          | 0.0652         |
+| 0.9524 | 20   | 0.2181        | 0.2286          | 0.0535         |
+| 1.1905 | 25   | 0.2774        | 0.1610          | 0.0694         |
+| 1.4286 | 30   | 0.1948        | 0.1818          | 0.0733         |
+| -1     | -1   | -             | -               | 0.0733         |
+| 0.2381 | 5    | 0.1696        | 0.1475          | 0.0705         |
+| 0.4762 | 10   | 0.1657        | 0.2067          | 0.0661         |
+| 0.7143 | 15   | 0.1346        | 0.1991          | 0.0635         |
+| 0.9524 | 20   | 0.1197        | 0.1466          | 0.0473         |
+| 1.1905 | 25   | 0.2657        | 0.1380          | 0.0544         |
+| 1.4286 | 30   | 0.1706        | 0.1906          | 0.0719         |
+| 1.6667 | 35   | 0.1686        | 0.1746          | 0.0741         |
+| 1.9048 | 40   | 0.1217        | 0.1577          | 0.0669         |
+| 2.1429 | 45   | 0.1191        | 0.1355          | 0.0606         |
+| 2.3810 | 50   | 0.108         | 0.1362          | 0.0615         |
+| 2.6190 | 55   | 0.1065        | 0.1595          | 0.0647         |
+| 2.8571 | 60   | 0.1314        | 0.1126          | 0.0667         |
+| 3.0952 | 65   | 0.072         | 0.0934          | 0.0589         |
+| 3.3333 | 70   | 0.0868        | 0.0977          | 0.0655         |
+| 3.5714 | 75   | 0.0719        | 0.1310          | 0.0496         |
+| 3.8095 | 80   | 0.1184        | 0.1388          | 0.0681         |
+| 4.0476 | 85   | 0.0997        | 0.1132          | 0.0656         |
+| 4.2857 | 90   | 0.0659        | 0.1029          | 0.0724         |
+| 4.5238 | 95   | 0.0554        | 0.1018          | 0.0707         |
+| 4.7619 | 100  | 0.0729        | 0.0989          | 0.0659         |
+| 5.0    | 105  | 0.0422        | 0.0971          | 0.0735         |
+| -1     | -1   | -             | -               | 0.0735         |
+
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.2
+- Transformers: 4.57.6
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.12.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### TripletLoss
+```bibtex
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,70 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 129,
+  "tie_word_embeddings": true,
+  "tokenizer_class": "GemmaTokenizerFast",
+  "transformers_version": "5.0.0",
+  "unsloth_version": "2026.1.4",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.2",
+    "transformers": "5.0.0",
+    "pytorch": "2.9.0+cpu"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6033f19eb1e6999d8daf87ac6e6845dc43f1b8cfacd786b122908ff00c86d8ea
+size 1211486072

modules.json

@@ -0,0 +1,32 @@
+[
+  {
+    "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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 768,
+    "do_lower_case": false
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7496f19b8099821eb489dbc4f880dd342842dd931fd4e8a111b70fd00d89853
+size 33384883

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "mask_token": "<mask>",
+  "model_max_length": 768,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}