Update README.md
Browse files
README.md
CHANGED
@@ -8,3 +8,69 @@ pinned: false
|
|
8 |
---
|
9 |
|
10 |
Edit this `README.md` markdown file to author your organization card.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
Edit this `README.md` markdown file to author your organization card.
|
11 |
+
|
12 |
+
## About
|
13 |
+
|
14 |
+
NextGen Technologies Research Foundation (in short, NGTRF) is an initiative to research Natural Language Processing, Machine Translation for Indian languages and also research Quantum Computing and Deep Learning.
|
15 |
+
Objective
|
16 |
+
|
17 |
+
The NGTRF aims to
|
18 |
+
|
19 |
+
Build NLP/MT models in Indian Languages,
|
20 |
+
Fine-tuned existing models for Indian Languages, and
|
21 |
+
Train Enthusiasts in these areas.
|
22 |
+
|
23 |
+
The data, code, and models will be available to the public for research and non-commercial purposes.
|
24 |
+
## Why NGTRF
|
25 |
+
|
26 |
+
First: Though many LLMs support multilingual, including Odia language, the performance for various tasks (e.g., content generation, question-answering) is limited due to the amount of ingested data for Odia.
|
27 |
+
|
28 |
+
Second: There are subscriptions or fees associated with the high-performing LLMs.
|
29 |
+
|
30 |
+
Third: The usage (privacy) and bias of data input to these LLMs are in question.
|
31 |
+
|
32 |
+
## What are the focus research areas of NGTRF
|
33 |
+
|
34 |
+
We have divided the primary focus areas into three parts.
|
35 |
+
|
36 |
+
1. Literature Survey: Investigate the latest developments in NLP/MT/QC domains and analyze current methods to support different tasks.
|
37 |
+
|
38 |
+
2. Development: Developing pre-trained and fine-tuned models, which includes dataset preparation, model training, evaluation, prompt engineering, and API development.
|
39 |
+
|
40 |
+
3. Deployment: Deploy the models for public access for research and non-commercial purposes.
|
41 |
+
## Who can use NGTRF Models
|
42 |
+
|
43 |
+
The models (pre-trained/fine-tuned) will be available through Hugging Face for research and non-commercial purposes. Feel free to contact us for a domain-specific application or particular use cases.
|
44 |
+
## What are the use cases of these models
|
45 |
+
|
46 |
+
There are several use cases of these models. Three primary domains relating to Rajasthan which we are focusing to use the developed models are:
|
47 |
+
|
48 |
+
Education
|
49 |
+
Healthcare
|
50 |
+
Governance
|
51 |
+
Tourism
|
52 |
+
Agriculture
|
53 |
+
Industrial Application
|
54 |
+
|
55 |
+
Contributors
|
56 |
+
|
57 |
+
Nisheeth Joshi
|
58 |
+
|
59 |
+
Iti Mathur
|
60 |
+
|
61 |
+
Pragya Katyayan
|
62 |
+
|
63 |
+
Palak Khurana
|
64 |
+
|
65 |
+
Riya Lonchenpa
|
66 |
+
|
67 |
+
Anju Krishnia
|
68 |
+
|
69 |
+
Vaishali Vaswani
|
70 |
+
|
71 |
+
Martina David
|
72 |
+
|
73 |
+
|
74 |
+
## License
|
75 |
+
|
76 |
+
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
|