sentence-transformers How to use phgelado/finbeddings_bert with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("phgelado/finbeddings_bert")
sentences = [
"what is the purpose of a mood board",
"Antigua and Barbuda Antigua and Barbuda (/ænˈtiːɡə ənd bɑːrˈbjuːdə/ ( listen); an-TEE-gǝ ǝnd bar-BEW-dǝ) is a sovereign state in the Americas, lying between the Caribbean Sea and the Atlantic Ocean. It consists of two major islands, Antigua and Barbuda, and a number of smaller islands (including Great Bird, Green, Guiana, Long, Maiden and York Islands and further south, the island of Redonda). The permanent population numbers about 81,800 (at the 2011 Census) and the capital and largest port and city is St. John's, on Antigua.",
"Mood board Graphic designers, interior designers, industrial designers, photographers and other creative artists use mood boards to visually illustrate the style they wish to pursue. However, these boards can also be used by design professionals to visually explain a certain style of writing, or an imaginary setting for a storyline. In short, mood boards are not limited to visual subjects, but serve as a visual tool to quickly inform others of the overall \"feel\" (or \"flow\") of an idea.[citation needed] In creative processes, mood boards can balance coordination and creative freedom.[2]",
"Misophonia As of 2016 the literature on misophonia was limited.[1] Some small studies show that people with misophonia generally have strong negative feelings, thoughts, and physical reactions to specific sounds, which the literature calls \"trigger sounds\". These sounds are apparently usually soft, but can be loud. One study found that around 80% of the sounds were related to the mouth (eating, slurping, chewing or popping gum, whispering, etc.), and around 60% were repetitive. A visual trigger may develop related to the trigger sound.[1][3] It also appears that a misophonic reaction can occur in the absence of an actual sound.[1]"
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
