56 lines
1.5 KiB
Markdown
56 lines
1.5 KiB
Markdown
---
|
||
base_model: Qwen/Qwen3-4B-Instruct-2507
|
||
datasets:
|
||
- Hi-Satoh/test_dpo_dataset
|
||
language:
|
||
- en
|
||
license: apache-2.0
|
||
library_name: transformers
|
||
pipeline_tag: text-generation
|
||
tags:
|
||
- dpo
|
||
- unsloth
|
||
- qwen
|
||
- alignment
|
||
---
|
||
|
||
# ＜【課題】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 Objective
|
||
This model has been optimized using DPO to align its responses with preferred outputs, focusing on improving reasoning (Chain-of-Thought) and structured response quality based on the provided preference dataset.
|
||
|
||
## Training Configuration
|
||
- **Base model**: Qwen/Qwen3-4B-Instruct-2507
|
||
- **Method**: DPO (Direct Preference Optimization)
|
||
- **Epochs**: 2
|
||
- **Learning rate**: 1e-06
|
||
- **Beta**: 0.05
|
||
- **Max sequence length**: 4096
|
||
- **LoRA Config**: r=8, alpha=16 (merged into base)
|
||
|
||
## Usage
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
import torch
|
||
|
||
model_id = "Hi-Satoh/adv_sft3J_dpo_merged"
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||
model = AutoModelForCausalLM.from_pretrained(
|
||
model_id,
|
||
torch_dtype=torch.float16,
|
||
device_map="auto"
|
||
)
|
||
```
|
||
|
||
## Sources & License (IMPORTANT)
|
||
|
||
* **Training Data**: [Hi-Satoh/test_dpo_dataset]
|
||
* **License**: MIT License. (As per dataset terms).
|
||
* **Compliance**: Users must follow the original base model's license terms.
|