Y-J-Ju
/

ModernBERT-base-ColBERT

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:808728

loss:Distillation

Model card Files Files and versions Community

Y-J-Ju commited on 9 days ago

Commit

0ff3fc2

·

1 Parent(s): 0e0b084

update readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -239,8 +239,8 @@ nDCG@10 scores for multi-vector retrieval models
 | Model                       | SciFact   | NFCorpus | FiQA      | TREC-Covid |
 | --------------------------- | --------- | -------- | --------- | ---------- |
 | BERT                        | 71.5      | 34.2     | 35.0      | 69.9       |
-| ModernBERT-Base (in paper)  | 73.0      | **35.2** | 38.0      | 80.5       |
-| ModernBERT-Base (this repo) | **73.88** | 34.96    | **39.47** | 80.5       |
 ### Training Hyperparameters
 #### Non-Default Hyperparameters

 | Model                       | SciFact   | NFCorpus | FiQA      | TREC-Covid |
 | --------------------------- | --------- | -------- | --------- | ---------- |
 | BERT                        | 71.5      | 34.2     | 35.0      | 69.9       |
+| ModernBERT-Base (in paper)  | 73.0      | **35.2** | 38.0      | **80.5**   |
+| ModernBERT-Base (this repo) | **73.88** | 34.96    | **39.47** | 79.36      |
 ### Training Hyperparameters
 #### Non-Default Hyperparameters