prateekagrawal commited on
Commit
ce82499
1 Parent(s): 3219b63

Updated app.py and about.py

Browse files
__pycache__/multiapp.cpython-38.pyc ADDED
Binary file (1.09 kB). View file
 
app.py CHANGED
@@ -1,12 +1,6 @@
1
- from pandas.io.formats.format import return_docstring
2
  import streamlit as st
3
- import pandas as pd
4
- from transformers import AutoTokenizer,AutoModelForMaskedLM
5
- from transformers import pipeline
6
- import os
7
- import json
8
  from multiapp import MultiApp
9
- from apps import about,credits,inference
10
 
11
 
12
  def main():
@@ -16,6 +10,6 @@ def main():
16
  app.add_app("Credits", credits.app)
17
  app.run()
18
 
19
-
20
  if __name__ == "__main__":
21
- main()
 
 
1
  import streamlit as st
 
 
 
 
 
2
  from multiapp import MultiApp
3
+ from apps import about, credits, inference
4
 
5
 
6
  def main():
 
10
  app.add_app("Credits", credits.app)
11
  app.run()
12
 
13
+
14
  if __name__ == "__main__":
15
+ main()
apps/__pycache__/about.cpython-38.pyc CHANGED
Binary files a/apps/__pycache__/about.cpython-38.pyc and b/apps/__pycache__/about.cpython-38.pyc differ
 
apps/__pycache__/credits.cpython-38.pyc CHANGED
Binary files a/apps/__pycache__/credits.cpython-38.pyc and b/apps/__pycache__/credits.cpython-38.pyc differ
 
apps/__pycache__/inference.cpython-38.pyc CHANGED
Binary files a/apps/__pycache__/inference.cpython-38.pyc and b/apps/__pycache__/inference.cpython-38.pyc differ
 
apps/about.py CHANGED
@@ -1,8 +1,37 @@
1
  import streamlit as st
2
 
 
3
  def app():
4
- st.title('About')
5
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
 
7
-
8
-
 
1
  import streamlit as st
2
 
3
+
4
  def app():
5
+ # st.title("About")
6
+ st.markdown("<h1 style='text-align: center;'>About</h1>", unsafe_allow_html=True)
7
+ st.markdown("""## Introduction""")
8
+ st.markdown(
9
+ """**RoBERTa-hindi** is one of the many projects in the Flax/JAX community week organized by HuggingFace in collaboration with Google to make compute-intensive projects more practicable."""
10
+ )
11
+ st.markdown(
12
+ """It is a monolingual transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts."""
13
+ )
14
+
15
+ st.markdown("""## Datasets used""")
16
+ st.markdown(
17
+ """RoBERTa-Hindi has been pretrained on a huge corpus consisting of multiple datasets. The entire list of datasets used is mentioned below : """
18
+ )
19
+ st.markdown(
20
+ """
21
+ 1. OSCAR
22
+ 2. mC4
23
+ 3. Indic-glue
24
+ 4. Hindi-wikipedia-articles-172k
25
+ 5. Hindi-text-short-summarization corpus
26
+ 6. Hindi-text-short-and-large-summarization corpus
27
+ 7. Oldnewspaperhindi
28
+ 8. Samanantar
29
+ """
30
+ )
31
+
32
+ st.markdown(
33
+ """
34
+ ***NOTE: Some of the datasets are readily available on the HuggingFace Datasets while the team developed the rest as per the docs.***
35
+ """
36
+ )
37