初始化项目，由ModelHub XC社区提供模型

Model: MInAlA/llama3-dpo-merged Source: Original Platform
2026-07-21 05:37:09 +08:00
commit a6b959dc07
8 changed files with 211 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,12 @@
+---
+library_name: transformers
+tags:
+- trl
+- dpo
+datasets:
+- argilla/ultrafeedback-binarized-preferences
+base_model:
+- meta-llama/Llama-3.2-3B-Instruct
+---
+
+Llama-3.2-3B-Instruct aligned using DPO on the ``argilla/ultrafeedback-binarized-preferences``