jojo-ai-mst
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -58,17 +58,14 @@ Thus, MyanmarGPT-Chat is required to build a foundational model for question-ans
|
|
58 |
|
59 |
<!-- Provide a longer summary of what this model is. -->
|
60 |
|
61 |
-
|
62 |
-
|
63 |
- **Developed by:** [Min Si Thu](https://huggingface.co/jojo-ai-mst)
|
64 |
-
- **Funded by
|
65 |
-
- **Shared by [optional]:** [More Information Needed]
|
66 |
- **Model type:** GPT2
|
67 |
- **Language(s) (NLP):** Burmese, English
|
68 |
- **License:** CreativeML OpenRAIL-M
|
69 |
- **Finetuned from model [MyanmarGPT]:** [MyanmarGPT](https://huggingface.co/jojo-ai-mst/MyanmarGPT)
|
70 |
|
71 |
-
### Model Sources
|
72 |
|
73 |
<!-- Provide the basic links for the model. -->
|
74 |
|
@@ -76,13 +73,10 @@ Thus, MyanmarGPT-Chat is required to build a foundational model for question-ans
|
|
76 |
- **Paper [optional]:** [More Information Needed]
|
77 |
- **Demo [optional]:** [More Information Needed]
|
78 |
|
79 |
-
## Uses
|
80 |
-
|
81 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
82 |
-
|
83 |
### Direct Use
|
84 |
|
85 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
|
|
86 |
|
87 |
Originally crafted for text completion in Burmese, this model functions as a fundamental asset for various Natural Language Processing (NLP) tasks. Although its primary role is presently centered on aiding in text generation and completion, it harbors considerable potential for broader applications. Researchers and developers have the option to refine this model using specialized datasets, thereby expanding its utility to other NLP domains, including summarization and instruction-based tasks. Nevertheless, it is crucial to acknowledge that when dealing with high-stakes decisions or comprehending domain-specific terminology, additional specialized training for the model is advised to ensure optimal accuracy and reliability.
|
88 |
|
@@ -90,20 +84,15 @@ Originally crafted for text completion in Burmese, this model functions as a fun
|
|
90 |
|
91 |
Users need to recognize the inherent limitations and biases present in language models. Responsible usage is crucial, particularly in sensitive contexts, as this model is not designed to generate misleading or harmful content.
|
92 |
|
93 |
-
[More Information Needed]
|
94 |
|
95 |
## Bias, Risks, and Limitations
|
96 |
|
97 |
-
While the MyanmarGPT-Chat excels in handling general Burmese text about history of
|
98 |
|
99 |
-
[More Information Needed]
|
100 |
|
101 |
### Recommendations
|
102 |
|
103 |
-
|
104 |
-
|
105 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
106 |
-
|
107 |
## How to Get Started with the Model
|
108 |
|
109 |
```shell
|
@@ -137,10 +126,19 @@ generate_text("User: မြန်မာနိုင်ငံအကြောင
|
|
137 |
|
138 |
|
139 |
|
140 |
-
##
|
141 |
|
142 |
- MinSithu, MyanmarGPT, https://huggingface.co/jojo-ai-mst/MyanmarGPT, 1.1-SweptWood
|
143 |
|
144 |
-
##
|
145 |
|
146 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
<!-- Provide a longer summary of what this model is. -->
|
60 |
|
|
|
|
|
61 |
- **Developed by:** [Min Si Thu](https://huggingface.co/jojo-ai-mst)
|
62 |
+
- **Funded by:** Self
|
|
|
63 |
- **Model type:** GPT2
|
64 |
- **Language(s) (NLP):** Burmese, English
|
65 |
- **License:** CreativeML OpenRAIL-M
|
66 |
- **Finetuned from model [MyanmarGPT]:** [MyanmarGPT](https://huggingface.co/jojo-ai-mst/MyanmarGPT)
|
67 |
|
68 |
+
### Model Sources
|
69 |
|
70 |
<!-- Provide the basic links for the model. -->
|
71 |
|
|
|
73 |
- **Paper [optional]:** [More Information Needed]
|
74 |
- **Demo [optional]:** [More Information Needed]
|
75 |
|
|
|
|
|
|
|
|
|
76 |
### Direct Use
|
77 |
|
78 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
79 |
+
Question Answering GPT for Burmese Language.
|
80 |
|
81 |
Originally crafted for text completion in Burmese, this model functions as a fundamental asset for various Natural Language Processing (NLP) tasks. Although its primary role is presently centered on aiding in text generation and completion, it harbors considerable potential for broader applications. Researchers and developers have the option to refine this model using specialized datasets, thereby expanding its utility to other NLP domains, including summarization and instruction-based tasks. Nevertheless, it is crucial to acknowledge that when dealing with high-stakes decisions or comprehending domain-specific terminology, additional specialized training for the model is advised to ensure optimal accuracy and reliability.
|
82 |
|
|
|
84 |
|
85 |
Users need to recognize the inherent limitations and biases present in language models. Responsible usage is crucial, particularly in sensitive contexts, as this model is not designed to generate misleading or harmful content.
|
86 |
|
|
|
87 |
|
88 |
## Bias, Risks, and Limitations
|
89 |
|
90 |
+
While the MyanmarGPT-Chat excels in handling general Burmese text about the history of countries around the world, its effectiveness might be limited when dealing with daily-life spoken burmese words. Users are encouraged to perform comprehensive testing tailored to their specific use cases.
|
91 |
|
|
|
92 |
|
93 |
### Recommendations
|
94 |
|
95 |
+
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model.
|
|
|
|
|
|
|
96 |
## How to Get Started with the Model
|
97 |
|
98 |
```shell
|
|
|
126 |
|
127 |
|
128 |
|
129 |
+
## Citations [optional]
|
130 |
|
131 |
- MinSithu, MyanmarGPT, https://huggingface.co/jojo-ai-mst/MyanmarGPT, 1.1-SweptWood
|
132 |
|
133 |
+
## How to cite this project
|
134 |
|
135 |
+
```
|
136 |
+
@software{MyanmarGPT-Chat,
|
137 |
+
author = {{MinSiThu}},
|
138 |
+
title = {MyanmarGPT-Chat},
|
139 |
+
url = {https://huggingface.co/jojo-ai-mst/MyanmarGPT-Chat},
|
140 |
+
urldate = {2024-1-28}
|
141 |
+
date = {2024-1-28},
|
142 |
+
}
|
143 |
+
|
144 |
+
```
|