Added msmarco v2.1 doc segmented splade-v3 bindings #2890
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lintool
requested changes
Jul 9, 2025
Member
lintool
left a comment
There was a problem hiding this comment.
Hi @clides - few items:
- you need to update
toolsand commit the update so I can get access totools/topics-and-qrels/topics.rag24.test.splade-v3.tsv.gz - please create the
*nistvariants of the YAML - please add the README in the hgf repo
lintool
approved these changes
Jul 9, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces regression tests and documentation updates for the SPLADE-v3 model applied to the MS MARCO V2.1 segmented document corpus, supporting both cached query encoding and ONNX-based on-the-fly query encoding. Key changes include the addition of new regression configurations, templates, and documentation, as well as updates to the
IndexInfoenumeration and associated tests.Regression Tests and Documentation Updates:
Cached Query Encoding:
rag24-doc-segmented-test-umbrela.splade-v3.cached.yamlfor cached query encoding with SPLADE-v3, including metrics, topics, and model parameters.rag24-doc-segmented-test-umbrela.splade-v3.cached.templatefor generating regression test pages for cached queries.regressions-rag24-doc-segmented-test-umbrela.splade-v3.cached.mdbased on the template.ONNX Query Encoding:
rag24-doc-segmented-test-umbrela.splade-v3.onnx.yamlfor ONNX-based query encoding with SPLADE-v3, including metrics, topics, and model parameters.rag24-doc-segmented-test-umbrela.splade-v3.onnx.templatefor generating regression test pages for ONNX-based queries.regressions-rag24-doc-segmented-test-umbrela.splade-v3.onnx.mdbased on the template.Codebase Updates:
MSMARCO_V21_DOC_SEGMENTED_SPLADE_V3to theIndexInfoenumeration inIndexInfo.javato define the SPLADE-v3 index metadata.testNumPrebuiltIndexesto reflect the addition of the new index.