victormiller commited on
Commit
37e0b82
1 Parent(s): 9b18c90

Update main.py

Browse files
Files changed (1) hide show
  1. main.py +5 -2
main.py CHANGED
@@ -274,8 +274,11 @@ def intro():
274
  id="section3",
275
  ),
276
  Section(
277
- H2("Conclusion"),
278
-
 
 
 
279
  id="section4",
280
  ),
281
  id="inner-text",
 
274
  id="section3",
275
  ),
276
  Section(
277
+ H3("Full and Openly Documented Production Ready Pretraining Corpus"),
278
+ P("We cover every aspect of the decisions made to produce the dataset, including document selection, filtering, quality assurance, deduplication, standardization and PII. Our reasoning is thoroughly explained, ensuring transparency and replicability. "),
279
+ P("Our code is open sourced here[link to github]."),
280
+ P("The dataset is ready for immediate download directly from Hugging Face [link]."),
281
+ P("In the remainder of this blog post, we will walk you through the entire process and the rationale behind each decision. Enjoy!"),
282
  id="section4",
283
  ),
284
  id="inner-text",