30 lines
640 B
Markdown
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
|
|
|