Update README.md
Browse files
README.md
CHANGED
@@ -27,22 +27,23 @@ WangChanLion is a Multilingual, instruction-finetuned on Southeast Asian Languag
|
|
27 |
- Repository: https://github.com/vistec-AI/WangchanLion
|
28 |
- Demo: [demo_WangchanLion.ipynb - Colaboratory](https://colab.research.google.com/drive/1y_7oOU3ZJI0h4chUrXFL3K4kelW_OI2G?usp=sharing#scrollTo=4yN3Bo6iAH2L)
|
29 |
|
30 |
-
#
|
|
|
31 |
Intended to be used as an instruction-following model for reading comprehension, brainstorming, and creative writing.
|
32 |
|
33 |
-
|
34 |
The model can be finetuned for any typical instruction-following use cases.
|
35 |
|
36 |
-
|
37 |
We do not expect the models to perform well in math problems, reasoning, and factfulness.
|
38 |
|
39 |
-
|
40 |
We noticed similar limitations to other finetuned instruction followers, such as math problems, reasoning, and factfulness. Even though the models do not perform on the level that we expect them to be abused, they do contain undesirable biases and toxicity and should be further optimized for your particular use cases.
|
41 |
|
42 |
-
|
43 |
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. More information is needed for further recommendations.
|
44 |
|
45 |
-
#
|
46 |
Use the code [here](https://colab.research.google.com/drive/1y_7oOU3ZJI0h4chUrXFL3K4kelW_OI2G?usp=sharing#scrollTo=4yN3Bo6iAH2L) to get started with the model.
|
47 |
|
48 |
Or
|
|
|
27 |
- Repository: https://github.com/vistec-AI/WangchanLion
|
28 |
- Demo: [demo_WangchanLion.ipynb - Colaboratory](https://colab.research.google.com/drive/1y_7oOU3ZJI0h4chUrXFL3K4kelW_OI2G?usp=sharing#scrollTo=4yN3Bo6iAH2L)
|
29 |
|
30 |
+
# Use cases
|
31 |
+
## Direct Use
|
32 |
Intended to be used as an instruction-following model for reading comprehension, brainstorming, and creative writing.
|
33 |
|
34 |
+
## Downstream Use
|
35 |
The model can be finetuned for any typical instruction-following use cases.
|
36 |
|
37 |
+
## Out-of-Scope Use
|
38 |
We do not expect the models to perform well in math problems, reasoning, and factfulness.
|
39 |
|
40 |
+
## Bias, Risks, and Limitations
|
41 |
We noticed similar limitations to other finetuned instruction followers, such as math problems, reasoning, and factfulness. Even though the models do not perform on the level that we expect them to be abused, they do contain undesirable biases and toxicity and should be further optimized for your particular use cases.
|
42 |
|
43 |
+
## Recommendations
|
44 |
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. More information is needed for further recommendations.
|
45 |
|
46 |
+
# Get Started
|
47 |
Use the code [here](https://colab.research.google.com/drive/1y_7oOU3ZJI0h4chUrXFL3K4kelW_OI2G?usp=sharing#scrollTo=4yN3Bo6iAH2L) to get started with the model.
|
48 |
|
49 |
Or
|