sentence-transformers How to use llm-wizard/legal-ft with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("llm-wizard/legal-ft")
sentences = [
"What actions did Mr and Mrs Harris take that led to the revelation of the facts in the case?",
"Perplexity’s marketing activities include promoting on its Instagram account a massive billboard \nin Times Square from September 2024 which read “Congratulations Perplexity on 250 million \nquestions answered last month.”5 \n \n4 Discover New York with Perplexity, Perplexity AI (last visited Oct. 17, 2024), \nhttps://www.perplexity.ai/encyclopedia/discovernewyork. \n5 @perplexity.ai, Instagram (Sept. 4, 2024), \nhttps://www.instagram.com/perplexity.ai/p/C_g2TonSHC5. \nCase 1:24-cv-07984 Document 1 Filed 10/21/24 Page 8 of 42",
"31 \n \nstatus. It was not until Mr. and Mrs. Harris retained counsel, served a demand letter on May 22, \n2024, met with the then Assistant Superintendent and a lengthy “bulling investigation” that these \nfacts came to light. \nThe Defendant’s actions and conduct, by definition, was arbitrary and capricious as was \nthe imposition of discipline that was a gross abuse of discretion when it served as a catalyst for \nthis action. Similarly, the Defendants exceeded their authority by repeatedly doubling down on \ntheir acts and conduct when given the opportunity to reverse course. The adverse action taken was \nnot based on sound, objective, adopted and approved policies and procedures regarding the use of",
"website users, and licensing is transacted with individuals and entities residing in this State and \nDistrict. As such, the injuries alleged herein from Perplexity’s infringement and other unlawful \nconduct foreseeably occurred in this State and District. In addition, Perplexity or its agents reside \nin this District and may be found in this State and District. \n23. \nDefendant Perplexity is subject to the jurisdiction of this Court pursuant to N.Y. \nC.P.L.R. § 302(a)(1) and (3) as it has purposefully directed its activities at New York and has \nCase 1:24-cv-07984 Document 1 Filed 10/21/24 Page 7 of 42"
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
