Commit
·
34a4e01
1
Parent(s):
504b4a4
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,19 +24,19 @@ A score of 1 means the statement is correct according to commonsense, and a scor
|
|
| 24 |
This score is calibrated, so a score between 0 and 1 can be interpreted as Vera's confidence that the statement is correct.
|
| 25 |
|
| 26 |
- **Developed by:** Jiacheng Liu, Wenya Wang, Dianzhuo Wang, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi
|
| 27 |
-
- **Shared by [
|
| 28 |
- **Model type:** Transformers
|
| 29 |
- **Language(s) (NLP):** English
|
| 30 |
- **License:** MIT
|
| 31 |
-
- **Finetuned from model
|
| 32 |
|
| 33 |
-
### Model Sources
|
| 34 |
|
| 35 |
<!-- Provide the basic links for the model. -->
|
| 36 |
|
| 37 |
- **Repository:** <https://github.com/liujch1998/vera>
|
| 38 |
-
- **Paper
|
| 39 |
-
- **Demo
|
| 40 |
|
| 41 |
## Uses
|
| 42 |
|
|
@@ -48,7 +48,7 @@ This score is calibrated, so a score between 0 and 1 can be interpreted as Vera'
|
|
| 48 |
|
| 49 |
Vera is intended to predict the correctness of commonsense statements.
|
| 50 |
|
| 51 |
-
### Downstream Use
|
| 52 |
|
| 53 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
|
|
@@ -66,12 +66,6 @@ Vera is a research prototype and may make mistakes. Do not use for making critic
|
|
| 66 |
|
| 67 |
See the **Limitations and Ethics Statement** section of our paper.
|
| 68 |
|
| 69 |
-
### Recommendations
|
| 70 |
-
|
| 71 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
-
|
| 73 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
-
|
| 75 |
## How to Get Started with the Model
|
| 76 |
|
| 77 |
Use the code below to get started with the model.
|
|
@@ -100,7 +94,7 @@ with torch.no_grad():
|
|
| 100 |
|
| 101 |
You may also refer to <https://huggingface.co/spaces/liujch1998/vera/blob/main/app.py#L27-L98> for implementation.
|
| 102 |
|
| 103 |
-
## Citation
|
| 104 |
|
| 105 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 106 |
|
|
@@ -118,4 +112,4 @@ You may also refer to <https://huggingface.co/spaces/liujch1998/vera/blob/main/a
|
|
| 118 |
|
| 119 |
## Model Card Contact
|
| 120 |
|
| 121 |
-
Jiacheng Liu
|
|
|
|
| 24 |
This score is calibrated, so a score between 0 and 1 can be interpreted as Vera's confidence that the statement is correct.
|
| 25 |
|
| 26 |
- **Developed by:** Jiacheng Liu, Wenya Wang, Dianzhuo Wang, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi
|
| 27 |
+
- **Shared by:** [Jiacheng (Gary) Liu](https://liujch1998.github.io/)
|
| 28 |
- **Model type:** Transformers
|
| 29 |
- **Language(s) (NLP):** English
|
| 30 |
- **License:** MIT
|
| 31 |
+
- **Finetuned from model:** T5-v1.1-XXL
|
| 32 |
|
| 33 |
+
### Model Sources
|
| 34 |
|
| 35 |
<!-- Provide the basic links for the model. -->
|
| 36 |
|
| 37 |
- **Repository:** <https://github.com/liujch1998/vera>
|
| 38 |
+
- **Paper:** <https://arxiv.org/abs/2305.03695>
|
| 39 |
+
- **Demo:** <https://huggingface.co/spaces/liujch1998/vera>
|
| 40 |
|
| 41 |
## Uses
|
| 42 |
|
|
|
|
| 48 |
|
| 49 |
Vera is intended to predict the correctness of commonsense statements.
|
| 50 |
|
| 51 |
+
### Downstream Use
|
| 52 |
|
| 53 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
|
|
|
|
| 66 |
|
| 67 |
See the **Limitations and Ethics Statement** section of our paper.
|
| 68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
## How to Get Started with the Model
|
| 70 |
|
| 71 |
Use the code below to get started with the model.
|
|
|
|
| 94 |
|
| 95 |
You may also refer to <https://huggingface.co/spaces/liujch1998/vera/blob/main/app.py#L27-L98> for implementation.
|
| 96 |
|
| 97 |
+
## Citation
|
| 98 |
|
| 99 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 100 |
|
|
|
|
| 112 |
|
| 113 |
## Model Card Contact
|
| 114 |
|
| 115 |
+
[Jiacheng (Gary) Liu](https://liujch1998.github.io/)
|