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 = "your_id/your-repo-name"

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}]

input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
)

input_ids = input_ids.to(model.device)
outputs = model.generate(input_ids=input_ids, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sources & License (IMPORTANT)

Training Data: u-10bei/dpo-dataset-qwen-cot
Base model license: apache-2.0 (follow the base model terms).
Dataset license: follow the dataset card terms on Hugging Face.

arata1/dpo-qwen-cot-merged

qwen3-4b-dpo-qwen-cot-merged-by-toya

Training Objective

Training Configuration

Usage

Sources & License (IMPORTANT)

arata1/
dpo-qwen-cot-merged