victormiller
commited on
Commit
•
c2b0703
1
Parent(s):
a552bff
Update main.py
Browse files
main.py
CHANGED
@@ -129,7 +129,7 @@ intro_text = P("Pretraining performant large language models (LLMs) requires tri
|
|
129 |
A("Crystal-7B", href = "https://huggingface.co/LLM360/CrystalCoder"),
|
130 |
", ",
|
131 |
A("K2-65B", href = "https://huggingface.co/LLM360/K2"),
|
132 |
-
"have demonstrated how data curation is a ‘make-or-break’ decision for model quality and capability.",)
|
133 |
|
134 |
intro_list = P("We present TxT360, the Trillion eXtracted Text corpus, a 5.7T token dataset for pretraining projects that:")
|
135 |
|
|
|
129 |
A("Crystal-7B", href = "https://huggingface.co/LLM360/CrystalCoder"),
|
130 |
", ",
|
131 |
A("K2-65B", href = "https://huggingface.co/LLM360/K2"),
|
132 |
+
" have demonstrated how data curation is a ‘make-or-break’ decision for model quality and capability.",)
|
133 |
|
134 |
intro_list = P("We present TxT360, the Trillion eXtracted Text corpus, a 5.7T token dataset for pretraining projects that:")
|
135 |
|