hunterhector commited on
Commit
9cbd894
1 Parent(s): 4cc0103

work on some section stuff

Browse files
Files changed (4) hide show
  1. common.py +0 -1
  2. curated.py +2 -1
  3. main.py +4 -0
  4. results.py +1 -1
common.py CHANGED
@@ -464,7 +464,6 @@ global_div = Div(
464
  style="display: flex; justify-content: center; align-items: center; width: 100%; max-width: 100%; height: auto; overflow-x: auto;"
465
  )
466
  ),
467
- Section(H3("Conclusion"), P("NEED TO UPDATE")),
468
  )
469
 
470
 
 
464
  style="display: flex; justify-content: center; align-items: center; width: 100%; max-width: 100%; height: auto; overflow-x: auto;"
465
  )
466
  ),
 
467
  )
468
 
469
 
curated.py CHANGED
@@ -1722,11 +1722,12 @@ def curated():
1722
  return Div(
1723
  Section(
1724
  overview,
 
1725
  ),
1726
  Section(
1727
  curated_sources_intro,
1728
  plotly2fasthtml(treemap_chart),
1729
- id="section31",
1730
  ),
1731
  Section(
1732
  data_preprocessing_div,
 
1722
  return Div(
1723
  Section(
1724
  overview,
1725
+ id="section31",
1726
  ),
1727
  Section(
1728
  curated_sources_intro,
1729
  plotly2fasthtml(treemap_chart),
1730
+ # id="section31",
1731
  ),
1732
  Section(
1733
  data_preprocessing_div,
main.py CHANGED
@@ -874,6 +874,10 @@ def intro():
874
  D_cite(bibtex_key="redpajama-v2"),
875
  "we also hope to provide a dataset at this scale that is ready to go, without requiring futher filtering."
876
  ),
 
 
 
 
877
  id="section11",
878
  ),
879
  Section(
 
874
  D_cite(bibtex_key="redpajama-v2"),
875
  "we also hope to provide a dataset at this scale that is ready to go, without requiring futher filtering."
876
  ),
877
+ P(
878
+ B("How to Reaad this Blog Post?"),
879
+ P("This document contains all the details and is lengthy. We recommend readers to use the Table of Contents to jump to the appropriate sections. At each top level section, we provided a quick guide for the content. We also recommend readers to consider this post as a reference for some high level statistics related to pre-training datasets.")
880
+ ),
881
  id="section11",
882
  ),
883
  Section(
results.py CHANGED
@@ -764,7 +764,7 @@ intro_div = Div(
764
  Li("The Learning Curve of TxT360 with an Upsampling Recipe", style = "margin-bottom: 5px"),
765
  Li("Perplexity Analysis across time", style = "margin-bottom: 5px"),
766
  Li("Topic Analysis on Data Cluster Groups", style = "margin-bottom: 5px"),
767
- Li(B("Estimated Reading Time: 15 minutes"), style = "margin-bottom: 5px"),
768
  ),
769
  )
770
 
 
764
  Li("The Learning Curve of TxT360 with an Upsampling Recipe", style = "margin-bottom: 5px"),
765
  Li("Perplexity Analysis across time", style = "margin-bottom: 5px"),
766
  Li("Topic Analysis on Data Cluster Groups", style = "margin-bottom: 5px"),
767
+ Li(B("Estimated Reading Time: 25 minutes"), style = "margin-bottom: 5px"),
768
  ),
769
  )
770