patrickvonplaten's picture
model documentation (#1)
8ba1de0
---
tags:
- question-answering
- bert
---
# Model Card for biobert-large-cased-v1.1-squad
# Model Details
## Model Description
More information needed
- **Developed by:** DMIS-lab (Data Mining and Information Systems Lab, Korea University)
- **Shared by [Optional]:** DMIS-lab (Data Mining and Information Systems Lab, Korea University)
- **Model type:** Question Answering
- **Language(s) (NLP):** More information needed
- **License:** More information needed
- **Parent Model:** [gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B)
- **Resources for more information:**
- [GitHub Repo](https://github.com/jhyuklee/biobert)
- [Associated Paper](https://arxiv.org/abs/1901.08746)
# Uses
## Direct Use
This model can be used for the task of question answering.
## Downstream Use [Optional]
More information needed.
## Out-of-Scope Use
The model should not be used to intentionally create hostile or alienating environments for people.
# Bias, Risks, and Limitations
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
## Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
# Training Details
## Training Data
The model creators note in the [associated paper](https://arxiv.org/pdf/1901.08746.pdf):
> We used the BERTBASE model pre-trained on English Wikipedia and BooksCorpus for 1M steps. BioBERT v1.0 (þ PubMed þ PMC) is the version of BioBERT (þ PubMed þ PMC) trained for 470 K steps. When using both the PubMed and PMC corpora, we found that 200K and 270K pre-training steps were optimal for PubMed and PMC, respectively. We also used the ablated versions of BioBERT v1.0, which were pre-trained on only PubMed for 200K steps (BioBERT v1.0 (þ PubMed)) and PMC for 270K steps (BioBERT v1.0 (þ PMC))
## Training Procedure
### Preprocessing
The model creators note in the [associated paper](https://arxiv.org/pdf/1901.08746.pdf):
> We pre-trained BioBERT using Naver Smart Machine Learning (NSML) (Sung et al., 2017), which is utilized for large-scale experiments that need to be run on several GPUs
### Speeds, Sizes, Times
The model creators note in the [associated paper](https://arxiv.org/pdf/1901.08746.pdf):
> The maximum sequence length was fixed to 512 and the mini-batch size was set to 192, resulting in 98 304 words per iteration.
# Evaluation
## Testing Data, Factors & Metrics
### Testing Data
More information needed
### Factors
More information needed
### Metrics
More information needed
## Results
More information needed
# Model Examination
More information needed
# Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** More information needed
- **Training**: Eight NVIDIA V100 (32GB) GPUs [ for training],
- **Fine-tuning:** a single NVIDIA Titan Xp (12GB) GPU to fine-tune BioBERT on each task
- **Hours used:** More information needed
- **Cloud Provider:** More information needed
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
# Technical Specifications [optional]
## Model Architecture and Objective
More information needed
## Compute Infrastructure
More information needed
### Hardware
More information needed
### Software
More information needed.
# Citation
**BibTeX:**
```bibtex
@misc{mesh-transformer-jax,
@article{lee2019biobert,
title={BioBERT: a pre-trained biomedical language representation model for biomedical text mining},
author={Lee, Jinhyuk and Yoon, Wonjin and Kim, Sungdong and Kim, Donghyeon and Kim, Sunkyu and So, Chan Ho and Kang, Jaewoo},
journal={arXiv preprint arXiv:1901.08746},
year={2019}
}
```
# Glossary [optional]
More information needed
# More Information [optional]
For help or issues using BioBERT, please submit a GitHub issue. Please contact Jinhyuk Lee(`lee.jnhk (at) gmail.com`), or Wonjin Yoon (`wonjin.info (at) gmail.com`) for communication related to BioBERT.
# Model Card Authors [optional]
DMIS-lab (Data Mining and Information Systems Lab, Korea University) in collaboration with Ezi Ozoani and the Hugging Face team
# Model Card Contact
More information needed
# How to Get Started with the Model
Use the code below to get started with the model.
<details>
<summary> Click to expand </summary>
```python
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("dmis-lab/biobert-large-cased-v1.1-squad")
model = AutoModelForQuestionAnswering.from_pretrained("dmis-lab/biobert-large-cased-v1.1-squad")
```
</details>