ComparisonPO
/

Llama-3-Base-8B-DPO_clean

Model card Files Files and versions

PeterLauLukCh commited on Mar 17, 2025

Commit

bf16fa8

·

verified ·

1 Parent(s): 5e00751

Update README.md

Files changed (1) hide show

README.md +7 -3

README.md CHANGED Viewed

@@ -1,3 +1,7 @@
----
-license: mit
----

+---
+license: mit
+datasets:
+- trl-lib/ultrafeedback_binarized
+base_model:
+- princeton-nlp/Llama-3-Base-8B-SFT
+---