How to use nlpctx/bge-m3-telugu-codemix-embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nlpctx/bge-m3-telugu-codemix-embedding") sentences = [ "ఆన్లైన్ లో missing persons గురించి ఏ", "Missing Persons Information:\nTo find information about missing persons online, visit the Tamil Nadu Police Department's official website (tnpolice.gov.in) and click on the \"Missing Persons\" or \"Citizen Services\" section. You can also check the National Crime Records Bureau (NCRB) website (ncrb.gov.in) for missing persons data.", "Economic Offences Wing (EOW):\nThe Economic Offences Wing (EOW) handles cases related to economic crimes, such as cheating, forgery, and financial fraud. They investigate cases involving large-scale financial losses and white-collar crimes.", "Investigation Start Time:\nAfter filing an FIR, the investigation will start immediately. The police will verify the complaint and begin the inquiry process within 24 hours." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
The community tab is the place to discuss and collaborate with the HF community!
