初始化项目，由ModelHub XC社区提供模型

Model: Phantomcloak19/qwen2.5-3b-dpo-grpo
Source: Original Platform

README.md

@@ -0,0 +1,18 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: transformers
+tags:
+  - dpo-grpo
+  - qwen2.5-3b
+---
+# qwen2.5-3b — DPO-GRPO
+
+Merged full-precision model after the **DPO-GRPO** phase of the
+LLMPR sequential training pipeline (SFT → DPO → Safety-GRPO).
+
+| Field | Value |
+|---|---|
+| Base model | `Qwen/Qwen2.5-3B-Instruct` |
+| Phase | DPO-GRPO |
+| Short name | qwen2.5-3b |
+| Generated | 2026-06-30 03:11 UTC |