Files
dpo-qwen-cot-merged_dpo_v1_l2/README.md
ModelHub XC 08b3e0fc08 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
2026-06-11 20:19:45 +08:00

30 lines
640 B
Markdown

---
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