＜dpo-qwen-cot-mergedv2＞

This model is a fine-tuned version of NobutaMN/qwen3-4b-structevalt-lora-nobuta-v2change using Direct Preference Optimization (DPO) via the Unsloth library.

This repository contains LoRA adapter weights only. The base model must be loaded separately.

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: NobutaMN/qwen3-4b-structevalt-lora-nobuta-v2change
• Method: DPO (Direct Preference Optimization)
• Epochs: 1
• Learning rate: 1e-07
• Beta: 0.1
• Max sequence length: 1024
• LoRA Config: r=8, alpha=16

Usage

This is a LoRA adapter. Load the base model, then apply the adapter.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

base_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "your_id/your-repo-name"

tokenizer = AutoTokenizer.from_pretrained(base_id)
model = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.float16,
    device_map="auto"
)
from peft import PeftModel
model = PeftModel.from_pretrained(model, adapter_id)

# Test inference
prompt = "Your question here"
inputs = tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

Sources & License (IMPORTANT)

• Training Data: [u-10bei/dpo-dataset-qwen-cot-localchange]
• License: MIT License. (As per dataset terms).
• Compliance: Users must follow the original base model's license terms.