metadata
license: apache-2.0
language:
- en
datasets:
- ms_marco
tags:
- splade++
- document-expansion
- sparse representation
- bag-of-words
- passage-retrieval
- knowledge-distillation
- document encoder
pretty_name: >-
ONNX model for prithivida's Splade_PP_en_v2, an Independent Implementation of
SPLADE++ Model with some efficiency tweaks for Industry setting.
base_model: prithivida/Splade_PP_en_v2
ONNX model for Splade_PP_en_v2
See https://huggingface.co/prithivida/Splade_PP_en_v2
This is just a script for onnx conversion, and an onnx model, with an output format that is compatible with the anserini SparseEncoder implementations. Based on advice this github issue.
python splade_pp_en_v2_to_onnx.py splade_pp_en_v2.onnx