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

base_model	datasets	language	license	library_name	pipeline_tag	tags
sfutenma/lora_structeval_t_qwen3_4b_v260228-172650	u-10bei/dpo-dataset-qwen-cot	en	apache-2.0	transformers	text-generation	dpo unsloth qwen alignment

dpo-qwen3_4b-cot-merged_v260301-220140

This model is a fine-tuned version of sfutenma/lora_structeval_t_qwen3_4b_v260228-172650 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: sfutenma/lora_structeval_t_qwen3_4b_v260228-172650
• Method: DPO (Direct Preference Optimization)
• Epochs: 5
• Learning rate: 2e-05
• Beta: 0.03
• Max sequence length: 768
• LoRA Config: r=8, alpha=16 (merged into base)
• Early Stop: threshold=1.2

Usage

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

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "sfutenma/dpo-qwen3_4b-cot-merged_v260301-220140"

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"
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]
• License: MIT License. (As per dataset terms).
• Compliance: Users must follow the original base model's license terms.