Total runs:
585
Run Growth:
144
Growth Rate:
23.96%
Sponsored by
Vmake Labs Video Enhancer
sultan / BioM-ELECTRA-Large-Discriminator
Model's Last Updated: November 05 2023
Introduction of BioM-ELECTRA-Large-Discriminator
Model Details of BioM-ELECTRA-Large-Discriminator
BioM-Transformers: Building Large Biomedical Language Models with BERT, ALBERT and ELECTRA
Abstract
The impact of design choices on the performance of biomedical language models recently has been a subject for investigation. In this paper, we empirically study biomedical domain adaptation with large transformer models using different design choices. We evaluate the performance of our pretrained models against other existing biomedical language models in the literature. Our results show that we achieve state-of-the-art results on several biomedical domain tasks despite using similar or less computational cost compared to other models in the literature. Our findings highlight the significant effect of design choices on improving the performance of biomedical language models.
Model Description
This model was pre-trained on PubMed Abstracts only with biomedical domain vocabulary for 434K steps with a batch size of 4096 on TPUv3-512 unit.
In order to help researchers with limited resources to fine-tune larger models, we created an example with PyTorch XLA. PyTorch XLA ( https://github.com/pytorch/xla ) is a library that allows you to use PyTorch on TPU units, which is provided for free by Google Colab and Kaggle. Follow this example to work with PyTorch/XLA Link
Check our GitHub repo at https://github.com/salrowili/BioM-Transformers for TensorFlow and GluonNLP checkpoints. We also updated this repo with a couple of examples on how to fine-tune LMs on text classification and questions answering tasks such as ChemProt, SQuAD, and BioASQ.
Colab Notebook Examples
BioM-ELECTRA-LARGE on NER and ChemProt Task
BioM-ELECTRA-Large on SQuAD2.0 and BioASQ7B Factoid tasks
BioM-ALBERT-xxlarge on SQuAD2.0 and BioASQ7B Factoid tasks
Text Classification Task With HuggingFace Transformers and PyTorchXLA on Free TPU
Reproducing our BLURB results with JAX
Finetunning BioM-Transformers with Jax/Flax on TPUv3-8 with free Kaggle resource
Acknowledgment
We would like to acknowledge the support we have from Tensorflow Research Cloud (TFRC) team to grant us access to TPUv3 units.
Citation
@inproceedings{alrowili-shanker-2021-biom,
title = "{B}io{M}-Transformers: Building Large Biomedical Language Models with {BERT}, {ALBERT} and {ELECTRA}",
author = "Alrowili, Sultan and
Shanker, Vijay",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2021.bionlp-1.24",
pages = "221--227",
abstract = "The impact of design choices on the performance of biomedical language models recently has been a subject for investigation. In this paper, we empirically study biomedical domain adaptation with large transformer models using different design choices. We evaluate the performance of our pretrained models against other existing biomedical language models in the literature. Our results show that we achieve state-of-the-art results on several biomedical domain tasks despite using similar or less computational cost compared to other models in the literature. Our findings highlight the significant effect of design choices on improving the performance of biomedical language models.",
}
Runs of sultan BioM-ELECTRA-Large-Discriminator on huggingface.co
332
Total runs
1
24-hour runs
35
3-day runs
159
7-day runs
162
30-day runs
More Information About BioM-ELECTRA-Large-Discriminator huggingface.co Model
Url of BioM-ELECTRA-Large-Discriminator
BioM-ELECTRA-Large-Discriminator huggingface.co Url
Provider of BioM-ELECTRA-Large-Discriminator huggingface.co
Other API from sultan
Updated:November 09 2023
Total runs:
97
Run Growth:
12
Growth Rate:
12.37%
Total runs:
84
Run Growth:
47
Growth Rate:
57.32%
Total runs:
80
Run Growth:
22
Growth Rate:
28.95%
Total runs:
64
Run Growth:
46
Growth Rate:
47.92%
Total runs:
61
Run Growth:
38
Growth Rate:
62.30%
Total runs:
61
Run Growth:
38
Growth Rate:
61.29%
Total runs:
59
Run Growth:
20
Growth Rate:
35.09%
Total runs:
57
Run Growth:
31
Growth Rate:
54.39%
Total runs:
48
Run Growth:
-110
Growth Rate:
-224.49%
Total runs:
32
Run Growth:
20
Growth Rate:
57.14%
Total runs:
29
Run Growth:
4
Growth Rate:
12.90%
Total runs:
25
Run Growth:
6
Growth Rate:
22.22%
Total runs:
24
Run Growth:
4
Growth Rate:
15.38%
Total runs:
20
Run Growth:
8
Growth Rate:
36.36%
Total runs:
17
Run Growth:
8
Growth Rate:
42.11%
Total runs:
15
Run Growth:
-9
Growth Rate:
-56.25%
Total runs:
14
Run Growth:
-8
Growth Rate:
-50.00%
Total runs:
14
Run Growth:
-6
Growth Rate:
-40.00%
Total runs:
12
Run Growth:
-10
Growth Rate:
-71.43%
Total runs:
11
Run Growth:
4
Growth Rate:
33.33%
Total runs:
11
Run Growth:
3
Growth Rate:
27.27%
Total runs:
7
Run Growth:
1
Growth Rate:
11.11%
Total runs:
6
Run Growth:
-2
Growth Rate:
-25.00%