rasyosef
/

splade-mini

Feature Extraction

sentence-transformers

Generated from Trainer

dataset_size:1000000

loss:SpladeLoss

loss:SparseMarginMSELoss

text-embeddings-inference

Model card Files Files and versions Community

rasyosef commited on Jul 30

Commit

f622aaa

·

verified ·

1 Parent(s): 864b849

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -149,13 +149,13 @@ This tiny SPLADE model is `6x` smaller than Naver's official `splade-v3-distilbe
 ## Performance
-The splade models were evaluated on 55 thousand queries and 8 million documents from the [MSMARCO](https://huggingface.co/datasets/microsoft/ms_marco) dataset.
 ||Size (# Params)|MRR@10 (MS MARCO dev)|
 |:---|:----|:-------------------|
-|`BM25`|-|18.6|-|-|
-|`rasyosef/splade-tiny`|4.4M|30.8|
-|`rasyosef/splade-mini`|11.2M|32.8|
 |`naver/splade-v3-distilbert`|67.0M|38.7|
 ## Usage

 ## Performance
+The splade models were evaluated on 55 thousand queries and 8.84 million documents from the [MSMARCO](https://huggingface.co/datasets/microsoft/ms_marco) dataset.
 ||Size (# Params)|MRR@10 (MS MARCO dev)|
 |:---|:----|:-------------------|
+|`BM25`|-|18.0|-|-|
+|`rasyosef/splade-tiny`|4.4M|30.9|
+|`rasyosef/splade-mini`|11.2M|33.2|
 |`naver/splade-v3-distilbert`|67.0M|38.7|
 ## Usage