Text Generation
Transformers
PyTorch
Thai
English
mpt
custom_code
text-generation-inference
mrp commited on
Commit
729a5f4
1 Parent(s): 44a76d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -6
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
- # Direct Use
 
31
  Intended to be used as an instruction-following model for reading comprehension, brainstorming, and creative writing.
32
 
33
- # Downstream Use
34
  The model can be finetuned for any typical instruction-following use cases.
35
 
36
- # Out-of-Scope Use
37
  We do not expect the models to perform well in math problems, reasoning, and factfulness.
38
 
39
- # Bias, Risks, and Limitations
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
- # Recommendations
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
- # How to Get Started with the Model
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