Update overview.py
Browse files- overview.py +0 -4
overview.py
CHANGED
|
@@ -269,10 +269,6 @@ def get_curated_chart():
|
|
| 269 |
|
| 270 |
overview_div = Div(
|
| 271 |
Section(
|
| 272 |
-
Details(
|
| 273 |
-
Summary("Open Me"),
|
| 274 |
-
"maybe this will work"
|
| 275 |
-
),
|
| 276 |
H2("Combining the Best of Web and Curated Sources"),
|
| 277 |
P("""The quality and size of a pre-training dataset play a crucial role in the performance of large language models (LLMs).
|
| 278 |
The community has introduced a variety of datasets for this purpose, including purely web-based datasets like RefinedWeb{citation_obj.display_citation("refinedweb")}, RedPajama-Data-V2{citation_obj.display_citation("redpajama-v2")}, DCLM{citation_obj.display_citation("dclm")}, and FineWeb{citation_obj.display_citation("fineweb")},
|
|
|
|
| 269 |
|
| 270 |
overview_div = Div(
|
| 271 |
Section(
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
H2("Combining the Best of Web and Curated Sources"),
|
| 273 |
P("""The quality and size of a pre-training dataset play a crucial role in the performance of large language models (LLMs).
|
| 274 |
The community has introduced a variety of datasets for this purpose, including purely web-based datasets like RefinedWeb{citation_obj.display_citation("refinedweb")}, RedPajama-Data-V2{citation_obj.display_citation("redpajama-v2")}, DCLM{citation_obj.display_citation("dclm")}, and FineWeb{citation_obj.display_citation("fineweb")},
|