Hugging Face's logo

opensearch-project
/
opensearch-neural-sparse-encoding-multilingual-v1

Feature Extraction
sentence-transformers
Safetensors
Transformers
bert
fill-mask
learned sparse
opensearch
retrieval
passage-retrieval
document-expansion
bag-of-words
sparse-encoder
sparse
asymmetric
inference-free
splade
text-embeddings-inference
Model card Files
xet
 Community
2
zhichao-geng commited on
Commit
daaf07d
·
verified ·
1 Parent(s): f4851de

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -34,9 +34,10 @@ datasets:
34
  The model should be selected considering search relevance, model inference and retrieval efficiency(FLOPS). We benchmark models' performance on **MIRACL** benchmark (we exclude th since the uncased backbone can not encode it).
35
  **We recommend to use it with max_ratio pruning.**
36
 
37
- | Model | Inference-free for Retrieval | Model Parameters | AVG NDCG@10 | AVG FLOPS |
38
- |-------|------------------------------|------------------|-------------|-----------|
39
- | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1) | ✔️ | 160M | 0.629 | 1.3 |
 
40
 
41
  ## Overview
42
 
@@ -156,7 +157,7 @@ The above code sample shows an example of neural sparse search. Although there i
156
  |-------|---------|----|----|----|----|----|----|----|----|----|----|----|----|----|----|----|
157
  | BM25 | 0.305 | 0.482 | 0.383 | 0.077 | 0.115 | 0.297 | 0.350 | 0.256 | 0.395 | 0.175 | 0.287 | 0.312 | 0.458 | 0.351 | 0.371 | 0.267 |
158
  | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1) | 0.629 | 0.670 | 0.740 | 0.542 | 0.558 | 0.582 | 0.486 | 0.658 | 0.740 | 0.562 | 0.514 | 0.669 | 0.767 | 0.768 | 0.607 | 0.575 |
159
- | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1); prune_ratio 0.1 | 0.624 | 0.667 | 0.740 | 0.537 | 0.555 | 0.576 | 0.481 | 0.655 | 0.737 | 0.558 | 0.511 | 0.664 | 0.761 | 0.766 | 0.604 | 0.572 |
160
 
161
  </div>
162
 
 
34
  The model should be selected considering search relevance, model inference and retrieval efficiency(FLOPS). We benchmark models' performance on **MIRACL** benchmark (we exclude th since the uncased backbone can not encode it).
35
  **We recommend to use it with max_ratio pruning.**
36
 
37
+ | Model | Inference-free for Retrieval | Model Parameters | AVG NDCG@10 | AVG FLOPS | AVG EMB SIZE |
38
+ |-------|------------------------------|------------------|-------------|-----------| -----------|
39
+ | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1) | ✔️ | 160M | 0.629 | 1.3 | 138 |
40
+ | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1); prune_ratio 0.1 | ✔️ | 160M | 0.626 | 0.8 | 75 |
41
 
42
  ## Overview
43
 
 
157
  |-------|---------|----|----|----|----|----|----|----|----|----|----|----|----|----|----|----|
158
  | BM25 | 0.305 | 0.482 | 0.383 | 0.077 | 0.115 | 0.297 | 0.350 | 0.256 | 0.395 | 0.175 | 0.287 | 0.312 | 0.458 | 0.351 | 0.371 | 0.267 |
159
  | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1) | 0.629 | 0.670 | 0.740 | 0.542 | 0.558 | 0.582 | 0.486 | 0.658 | 0.740 | 0.562 | 0.514 | 0.669 | 0.767 | 0.768 | 0.607 | 0.575 |
160
+ | [opensearch-neural-sparse-encoding-multilingual-v1](https://huggingface.co/opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1); prune_ratio 0.1 | 0.626 | 0.667 | 0.740 | 0.537 | 0.555 | 0.576 | 0.481 | 0.655 | 0.737 | 0.558 | 0.511 | 0.664 | 0.761 | 0.766 | 0.604 | 0.572 |
161
 
162
  </div>
163