Hugging Face's logo

NeuML
/
pubmedbert-base-embeddings

Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
English
bert
feature-extraction
text-embeddings-inference
Model card Files
xet
 Community
3
davidmezzetti commited on
Commit
64beaa0
·
1 Parent(s): e6e0356

Update README

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -85,22 +85,22 @@ Performance of this model compared to the top base models on the [MTEB leaderboa
85
 
86
  The following datasets were used to evaluate model performance.
87
 
88
- - [PubMed QA](https://huggingface.co/datasets/pubmed_qa)
89
  - Subset: pqa_labeled, Split: train, Pair: (question, long_answer)
90
- - [PubMed Subset](https://huggingface.co/datasets/zxvix/pubmed_subset_new)
91
  - Split: test, Pair: (title, text)
92
- - [PubMed Summary](https://huggingface.co/datasets/scientific_papers)
93
  - Subset: pubmed, Split: validation, Pair: (article, abstract)
94
 
95
  Evaluation results are shown below. The [Pearson correlation coefficient](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) is used as the evaluation metric.
96
 
97
  | Model | PubMed QA | PubMed Subset | PubMed Summary | Average |
98
  | ----------------------------------------------------------------------------- | --------- | ------------- | -------------- | --------- |
99
- | [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | 90.40 | 95.86 | 94.07 | 93.44 |
100
- | [bge-base-en-v1.5](https://hf.co/BAAI/bge-large-en-v1.5) | 91.02 | 95.60 | 94.49 | 93.70 |
101
- | [gte-base](https://hf.co/thenlper/gte-base) | 92.97 | 96.83 | 96.24 | 95.35 |
102
- | [**pubmedbert-base-embeddings**](https://hf.co/neuml/pubmedbert-base-embeddings) | **93.27** | **97.07** | **96.58** | **95.64** |
103
- | [S-PubMedBert-MS-MARCO](https://hf.co/pritamdeka/S-PubMedBert-MS-MARCO) | 90.86 | 93.33 | 93.54 | 92.58 |
104
 
105
  ## Training
106
 
 
85
 
86
  The following datasets were used to evaluate model performance.
87
 
88
+ - [PubMed QA](https://huggingface.co/datasets/qiaojin/PubMedQA)
89
  - Subset: pqa_labeled, Split: train, Pair: (question, long_answer)
90
+ - [PubMed Subset](https://huggingface.co/datasets/awinml/pubmed_abstract_3_1k)
91
  - Split: test, Pair: (title, text)
92
+ - [PubMed Summary](https://huggingface.co/datasets/armanc/scientific_papers)
93
  - Subset: pubmed, Split: validation, Pair: (article, abstract)
94
 
95
  Evaluation results are shown below. The [Pearson correlation coefficient](https://en.wikipedia.org/wiki/Pearson_correlation_coefficient) is used as the evaluation metric.
96
 
97
  | Model | PubMed QA | PubMed Subset | PubMed Summary | Average |
98
  | ----------------------------------------------------------------------------- | --------- | ------------- | -------------- | --------- |
99
+ | [all-MiniLM-L6-v2](https://hf.co/sentence-transformers/all-MiniLM-L6-v2) | 90.40 | 95.92 | 94.07 | 93.46 |
100
+ | [bge-base-en-v1.5](https://hf.co/BAAI/bge-base-en-v1.5) | 91.02 | 95.82 | 94.49 | 93.78 |
101
+ | [gte-base](https://hf.co/thenlper/gte-base) | 92.97 | 96.90 | 96.24 | 95.37 |
102
+ | [**pubmedbert-base-embeddings**](https://hf.co/neuml/pubmedbert-base-embeddings) | **93.27** | **97.00** | **96.58** | **95.62** |
103
+ | [S-PubMedBert-MS-MARCO](https://hf.co/pritamdeka/S-PubMedBert-MS-MARCO) | 90.86 | 93.68 | 93.54 | 92.69 |
104
 
105
  ## Training
106