adv_MoE_final_1_merged

＜【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

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Hi-Satoh/adv_MoE_final_1_merged"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    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.