dpo-qwen-cot-merged/README.md

base_model, datasets, language, license, library_name, pipeline_tag, tags

base_model	datasets	language	license	library_name	pipeline_tag	tags
Qwen/Qwen3-4B-Instruct-2507	u-10bei/dpo-dataset-qwen-cot	en	apache-2.0	transformers	text-generation	dpo unsloth qwen alignment

ksiwork1127

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: 1
• Learning rate: 1e-07
• Beta: 0.1
• 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 = "KSIMNB/dpo-qwen-cot-merged"

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

prompt = "Your question here"
inputs = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

## Sources & License (IMPORTANT)
- Training Data: u-10bei/dpo-dataset-qwen-cot (please refer to the dataset card for license/terms)
- Base Model: Qwen/Qwen3-4B-Instruct-2507 (Apache-2.0)
- Compliance: Users must follow both the dataset terms and the base model license.