Add splade-pp-ed beir regression files

[justram]

• added yaml/template/docs
• modified README.md
• tested with the collection at /mnt/users/j587yang/collections/beir-v1.0.0
• related PR

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (ae498aa) 62.95% compared to head (14c9022) 62.96%.

Additional details and impacted files

@@            Coverage Diff            @@
##             master    #2270   +/-   ##
=========================================
  Coverage     62.95%   62.96%           
- Complexity     1271     1272    +1     
=========================================
  Files           196      196           
  Lines         11418    11418           
  Branches       1452     1452           
=========================================
+ Hits           7188     7189    +1     
  Misses         3708     3708           
+ Partials        522      521    -1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[lintool]

This is what we have right now:

% ls src/main/resources/regression/msmarco-* | grep splade
src/main/resources/regression/msmarco-passage-distill-splade-max.yaml
src/main/resources/regression/msmarco-passage-splade-distil-cocodenser-medium.yaml
src/main/resources/regression/msmarco-passage-splade-pp-ed-onnx.yaml
src/main/resources/regression/msmarco-passage-splade-pp-ed.yaml
src/main/resources/regression/msmarco-passage-splade-pp-sd-onnx.yaml
src/main/resources/regression/msmarco-passage-splade-pp-sd.yaml
src/main/resources/regression/msmarco-v2-passage-splade-pp-ed.yaml
src/main/resources/regression/msmarco-v2-passage-splade-pp-sd.yaml

Let's be consistent and call it splade-pp-ed?

[justram]

model renamed

[lintool]

Awesome, thanks @justram for this!

Let's get this merged in, and I'll run tests on my end.

[justram]

Happy to help!
Pre-encoded documents can be found in the following directory: tjena:/mnt/users/j587yang/collections/beir-v1.0.0/splade-pp-ed. Need to transfer these documents to the respective servers such as orca, tuna, and others before initiating the regression process.

[lintool]

Happy to help! Pre-encoded documents can be found in the following directory: tjena:/mnt/users/j587yang/collections/beir-v1.0.0/splade-pp-ed. Need to transfer these documents to the respective servers such as orca, tuna, and others before initiating the regression process.

yup, will do!