Sentence Similarity
sentence-transformers
Safetensors
mpnet
feature-extraction
Generated from Trainer
dataset_size:3067
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use bdanko/umsb-mpnet-episodic-memory with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use bdanko/umsb-mpnet-episodic-memory with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("bdanko/umsb-mpnet-episodic-memory") sentences = [ "um according to dosing instructions. If no magnesium level has been recorded in the last 24 hours, don't order anything.\nmodel_prediction_summary: {\"finish_result\": \"[\\\"The patient S6537563's last serum magnesium level within the last 24 hours was 2.1 mg/dL (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the normal range (>= 1.9 mg/dL) and not low according to the provided dosing instructions, no replacement IV magnesium was ordered.\\\"]\", \"status\": \"completed\"}", "model correctly identified the age of the patient with MRN S6542579 as 28 based on the provided context and patient data\nAlthough the official reference solution pass flag was false (likely due to an internal evaluation error or missing expected output in the prompt metadata), the model's answer is factually correct according to the standard dataset associated with this MRN and the", "he rate such as \\\"h\\\" \", \"type\": \"string\"}, \"value\": {\"type\": \"number\"}}, \"type\": \"object\"}}, \"type\": \"object\"}, \"type\":\n\"array\"}, \"route\": {\"properties\": {\"text\": {\"description\": \"The medication route.\", \"type\": \"string\"}}, \"type\": \"object\"}}, \"type\": \"object\"}, \"type\": \"array\"}, \"intent\": {\"description\": \"Use \\\"order\\\" \", \"type\": \"string\"}, \"medicationCodeableConcept\": {\"properties\": {\"coding\": {\"items\": {\"properties\": {\"code\": {\"description\": \"The actual code\", \"type\": \"string\"}, \"display\": {\"description\": \"Display name\", \"type\": \"string\"}, \"system\": {\"description\": \"Coding system such as \\\"http://hl7.org/fhir/sid/ndc\\\" \", \"type\": \"string\"}}, \"type\": \"object\"}, \"type\": \"array\"}, \"text\": {\"description\": \"The order display name of the medication, otherwise the record name.\", \"type\": \"string\"}}, \"type\": \"object\"}, \"resourceType\": {\"description\": \"Use \\\"MedicationRequest\\\" for medication requests.\", \"type\": \"string\"}, \"status\": {\"description\": \"The status of the medication request", "um according to dosing instructions. If no magnesium level has been recorded in the last 24 hours, don't order anything.\nmodel_prediction_summary: {\"finish_result\": \"[\\\"The patient S6537563's last serum magnesium level within the last 24 hours was 2.1 mg/dL (recorded at 2023-11-13T04:24:00+00:00). Since this value is within the normal range (>= 1.9 mg/dL) and not low according to the provided dosing instructions, no replacement IV magnesium was ordered.\\\"]\", \"status\": \"completed\"}" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
File too large to display, you can check the raw version instead.