datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
CMMLU-Clinical-Knowledge-Benchmark
💻 Dataset Usage
Run the following command to load the testing set (237 examples):
from datasets import load_dataset
dataset = load_dataset("shuyuej/CMMLU-Clinical-Knowledge-Benchmark", split="train")
print(dataset)
Spanish-MMLU-Clinical-Knowledge-Benchmark
💻 Dataset Usage
Run the following command to load the testing set:
from datasets import load_dataset
dataset = load_dataset("shuyuej/Spanish-MMLU-Clinical-Knowledge-Benchmark", split="test")
print(dataset)
French-MMLU-Clinical-Knowledge-Benchmark
💻 Dataset Usage
Run the following command to load the testing set:
from datasets import load_dataset
dataset = load_dataset("shuyuej/French-MMLU-Clinical-Knowledge-Benchmark", split="test")
print(dataset)
BioMistral-Clinical-Knowledge-BaseThe datasets original from https://huggingface.co/datasets/AGBonnet/augmented-clinical-notes and embedded by https://huggingface.co/jinaai/jina-embeddings-v3
How to use
How to use this datasets for BioMistral-Clinical System:
from datasets import load_dataset
ds = load_dataset("ZiweiChen/BioMistral-Clinical-Knowledge-Base")
Load as clinical knowledge base
import numpy as np
train_dataset = ds['train']
text_data = train_dataset['text']
embedding_data =… See the full description on the dataset page: https://huggingface.co/datasets/ZiweiChen/BioMistral-Clinical-Knowledge-Base.MMLU-Clinical-Knowledge-Benchmark
💻 Dataset Usage
Run the following command to load the testing set (265 examples):
from datasets import load_dataset
dataset = load_dataset("shuyuej/MMLU-Clinical-Knowledge-Benchmark", split="test")
print(dataset)
Hindi-MMLU-Clinical-Knowledge-Benchmark
💻 Dataset Usage
Run the following command to load the testing set (265 examples):
from datasets import load_dataset
dataset = load_dataset("shuyuej/Hindi-MMLU-Clinical-Knowledge-Benchmark", split="test")
print(dataset)
mmlu-clinical-knowledge