How to use sahithkumar7/mpnet-base-smartbots-iter02-peft with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sahithkumar7/mpnet-base-smartbots-iter02-peft") sentences = [ "How many different active substances were detected in surface water across all catchment areas?", "metabolites were not detected in the water bodies.\n2.1.1. Antibiotics/Enzyme-Inhibitors and\nAbacavir in Surface-Water\nFifty detections were found in all catchment areas in surface water, which corresponds to 15 different active substances:\n12 antibiotics, two enzyme inhibitors, and one antiviral. The number of detections per sampling station ranged from 0 to 7\ndifferent active substances. The Ave river-Prazins (Santo Tirso) and Serzedelo I and II (Guimar ã es) as well as Ria\nFormosa-coastal water (Faro and Olh ã o), each one with two sampling sites, showed the most detected compounds in", "2. Results\n2.1. Frequency of Detections:\nAntibiotics/Enzyme-Inhibitors and Abacavir\nin Surface-Groundwater\nDuring the screening framework beyond the antibiotics/enzyme-inhibitors, the antiviral abacavir was detected. Therefore,\ngiven the relevance of this compound, it was included in the present study. Although enzyme inhibitors belong to the\nantibiotic group, their specific pharmacological properties and detection were sorted apart. In the present study, antibiotic\nmetabolites were not detected in the water bodies.\n2.1.1. Antibiotics/Enzyme-Inhibitors and\nAbacavir in Surface-Water", "surface water. The relatively higher detection of substances downstream of the effluent discharge points compared with a\nlow detection in upstream samples could be attributed to the low efficiency in urban wastewater treatment plants or\nagricultural pressure. The environmental impact is more critical due to active substances in drinking water or premix\nmedicated feeds in the veterinary site.\nFurthermore, the detection of substances of exclusive human use (abacavir, tazobactam and cilastatin) prove the weak" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
https://huggingface.co/sahithkumar7/mpnet-base-smartbots-iter02-peft/resolve/main/tokenizer.json
hf download hf://sahithkumar7/mpnet-base-smartbots-iter02-peft/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/sahithkumar7/mpnet-base-smartbots-iter02-peft/resolve/main/tokenizer.json
