Text Ranking
sentence-transformers
Safetensors
Korean
English
modernbert
cross-encoder
reranker
korean
english
text-embeddings-inference
Instructions to use nlpai-lab/KURE-Reranker-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nlpai-lab/KURE-Reranker-nano with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("nlpai-lab/KURE-Reranker-nano") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
Use full KURE-Reranker names in the figure and fix a missing space in the PPS note
#2
by yjoonjang - opened
- README.md +1 -1
- assets/pps_vs_ndcg9.png +2 -2
README.md
CHANGED
|
@@ -143,7 +143,7 @@ The figure plots mean nDCG@10 against mean PPS across the nine Korean benchmarks
|
|
| 143 |
| telepix/PIXIE-Spell-Reranker-Preview-0.6B | 596M | 0.7806 | 99.6 |
|
| 144 |
| cross-encoder/ettin-reranker-1b-v1 | 1.0B | 0.6901 | 49.7 |
|
| 145 |
|
| 146 |
-
PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over the nine benchmarks.Inputs are length-sorted and dynamically padded within each batch.
|
| 147 |
|
| 148 |
`jinaai/jina-reranker-v3` and `jinaai/jina-reranker-v3.5` are listwise rerankers that cannot be compared under the same 8,192-token condition on MLDR, so they are excluded from the 9-subset table and their MLDR cells are left blank below.
|
| 149 |
|
|
|
|
| 143 |
| telepix/PIXIE-Spell-Reranker-Preview-0.6B | 596M | 0.7806 | 99.6 |
|
| 144 |
| cross-encoder/ettin-reranker-1b-v1 | 1.0B | 0.6901 | 49.7 |
|
| 145 |
|
| 146 |
+
PPS is measured on a single NVIDIA RTX A6000 48GB per model and averaged over the nine benchmarks. Inputs are length-sorted and dynamically padded within each batch.
|
| 147 |
|
| 148 |
`jinaai/jina-reranker-v3` and `jinaai/jina-reranker-v3.5` are listwise rerankers that cannot be compared under the same 8,192-token condition on MLDR, so they are excluded from the 9-subset table and their MLDR cells are left blank below.
|
| 149 |
|
assets/pps_vs_ndcg9.png
CHANGED
|
Git LFS Details
|
|
Git LFS Details
|