sentence-transformers How to use kokojake/modernbert-embed-base-fitness-health-matryoshka with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("kokojake/modernbert-embed-base-fitness-health-matryoshka")
sentences = [
"= little to no difference (low certainty)\n \t\n= little to no difference (moderate certainty)\n= benefit that meets threshold for clinically important difference (very low certainty) = benefit that meets threshold for clinically important difference (low certainty)\n\t\n= benefit that meets threshold for clinically important difference (moderate certainty).\n53\n4. Evidence and recommendations\nIntervention class B: Physical interventions •\t In the comparison of any structured \nexercise programme with usual care \n(6 trials), trivial benefits were observed for \npain and function. Since the certainty of the \nevidence was very low for other time-points and outcomes, it was uncertain whether \nany structured exercise programme: \n\t›\n\tdecreased pain in the immediate term \n(trivial effect);\n\t›\n\tmade little to no difference to pain in the short term or long term;\n\t›\n\timproved function in the immediate \nterm (trivial effect);\n\t›\n\tmade little to no difference to function \nin the short term; or\n\t› improved function in the long term. \nIn the two trials on older people, trivial \nbenefit was observed for function. Since the \ncertainty of the evidence was very low, it was uncertain whether any structured exercise \nprogramme:\n\t›\n\tmade little to no difference to pain in \nthe immediate term (2 trials) or short \nterm (1 trial);\n\t› improved function the immediate term \n(trivial effect, 2 trials); or\n\t›\n\tmade little to no difference to function \nin the short term (1 trial).\nIn the two trials that monitored harms,",
"voice functions assessment techniques and impairments",
"physiotherapy exercises for patients with casts",
"effectiveness of exercise on function in older adults"
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
