How to use aryanmagoon/ms_marco_bi_encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("aryanmagoon/ms_marco_bi_encoder") sentences = [ "which type of tides have the largest range", "Your BMI is based on your height and weight. It's one way to see if you're at a healthy weight. Underweight: Your BMI is less than 18.5. Healthy weight: Your BMI is 18.5 to 24.9. Overweight: Your BMI is 25 to 29.9. Obese: Your BMI is 30 or higher. The chart below shows examples of body mass indexes. The figure at which your height corresponds with your weight is your body mass index.", "For example, a slight color change in the test pad for protein may indicate a small amount of protein present in the urine whereas a deep color change may indicate a large amount. The most frequently performed chemical tests using reagent test strips are: 1 Specific gravity.", "When the moon is full or new, the gravitational pull of the moon and sun are combined. At these times, the high tides are very high and the low tides are very low. This is known as a spring high tide. Spring tides are especially strong tides (they do not have anything to do with the season Spring). They occur when the Earth, the Sun, and the Moon are in a line. The gravitational forces of the Moon and the Sun both contribute to the tides. Spring tides occur during the full moon and the new moon." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4]
https://huggingface.co/aryanmagoon/ms_marco_bi_encoder/resolve/main/tokenizer.json
hf download hf://aryanmagoon/ms_marco_bi_encoder/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/aryanmagoon/ms_marco_bi_encoder/resolve/main/tokenizer.json
