lora-structeval-sft-0205-merged-v2

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 a LoRA adapter trained with DPO on top of the SFT adapter. You need to load the base model and then load this adapter using PEFT.

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: 1
• Learning rate: 5e-08
• Beta: 0.05
• Max sequence length: 1024
• LoRA Config: r=8, alpha=16 (merged into base)

Usage

Since this is a merged model, you can use it directly with transformers.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "lora-structeval-sft-0205-merged-v2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Test inference
prompt = "Your question here"

messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(
    text,
    return_tensors="pt",
).to("cuda")

outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sources & License (IMPORTANT)

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