初始化项目，由ModelHub XC社区提供模型

Model: Chiaki111/dpo-qwen-cot-merged_dpo_v1_l2
Source: Original Platform

README.md

@@ -0,0 +1,29 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/dpo-dataset-qwen-cot
+language:
+- en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- dpo
+- unsloth
+- qwen
+- alignment
+---
+
+# qwen3-4b-dpo-qwen-cot-merged
+
+This model is a fine-tuned version of **Qwen/Qwen3-4B-Instruct-2507** using **Direct Preference Optimization (DPO)** via the **Unsloth** library.
+
+This repository contains the **full-merged 16-bit weights**. No adapter loading is required.
+
+## Training Configuration
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Epochs: 1
+- Learning rate: 1e-06
+- Beta: 0.1
+- Max sequence length: 1024
+