Downloads · 30 days
11
2% of all-time downloads
bert-large-cuad
nikotang/bert-large-cuad
bert-large-cuad is a question answering model from nikotang. Use it when the input is a question plus a passage. It is set up for transformers.
This is a BERT-large model ([bert-large-uncased-whole-word-masking][2]) fine-tuned on the [CUAD][3] dataset from [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review (Hendrycks et al., 2021)][1], with the…
All-time downloads
611
Public
Repo size
2.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 94%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Apr 13, 2023
- Updated
- Apr 13, 2023
- SHA
- e5ae82a6
Try a prompt
Datasets
Model card
From the Hugging Face model README
BERT-large fine-tuned on CUAD
This is a BERT-large model (bert-large-uncased-whole-word-masking) fine-tuned on the CUAD dataset
from CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review (Hendrycks et al., 2021), with the BertforQuestionAnswering model architecture.
The questions ask for information often found in contracts; the model would return the relevant text string and its starting index in the given document if the information exists. The CUAD dataset is in SQuAD 2.0 format.
For details of the dataset and usage of the relevant training/testing scripts, check out the paper and their Github repo.
- Task
- Question Answering
- Library
- transformers
- Type
- bert
- Languages
- en
- Created
- Apr 13, 2023
- Updated
- Apr 13, 2023