初始化项目，由ModelHub XC社区提供模型

Model: thu-ml/STAIR-Qwen2-7B-DPO-3 Source: Original Platform
2026-04-23 09:22:09 +08:00
commit 7ffdc3bf2e
22 changed files with 152105 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 0.992,
+    "total_flos": 8638359306240.0,
+    "train_loss": 0.8013531161892798,
+    "train_runtime": 531.301,
+    "train_samples_per_second": 7.529,
+    "train_steps_per_second": 0.058
+}