Anush008's picture
Update README.md
78b113a verified
|
raw
history blame
1.19 kB
metadata
license: apache-2.0
language:
  - en
pipeline_tag: sentence-similarity

ONNX port of sentence-transformers/all-MiniLM-L6-v2 adjusted to return attention weights.

This model is intended to be used for BM42 searches.

Usage

Here's an example of performing inference using the model with FastEmbed.

from fastembed import SparseTextEmbedding

documents = [
    "You should stay, study and sprint.",
    "History can only prepare us to be surprised yet again.",
]

model = SparseTextEmbedding(model_name="Qdrant/bm42-all-minilm-l6-v2-attentions")
embeddings = list(model.embed(documents))

# [
#     SparseEmbedding(values=array([0.26399775, 0.24662513, 0.47077307]),
#                     indices=array([1881538586, 150760872, 1932363795])),
#     SparseEmbedding(values=array(
#         [0.38320042, 0.25453135, 0.18017513, 0.30432631, 0.1373556]),
#                     indices=array([
#                         733618285, 1849833631, 1008800696, 2090661150,
#                         1117393019
#                     ]))
# ]