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	dpo_train_brushed_v4_balanced.json	en	apache-2.0	transformers	text-generation	dpo unsloth qwen alignment

東京大学 松尾・岩澤研究室　大規模言語モデル　応用講座2025-2026

Author and Acknowledgments

• Author: Toshiki Demizu (出水 利樹) — GitHub/Hugging Face ID: @demimomi
• Affiliation: ソフトバンク株式会社、MONET Technologies株式会社
• Course: Large Language Model Development Lecture Advanced (Winter 2025－2026)
• Participants: 3800名参加

メインコンペ(2026年2月2日～3月2日)

• 状況:

  2026年2月8日現在 293位（現時点で497人が提出） 0.70044点

  2026年2月11日現在 261位（現時点で646人が提出）0.73407点 https://huggingface.co/demimomi/demimomi44taomax-qwen3-4b-structured-output-lora

  T4（TPU）だと日次Limitにすぐ達するため、A100（GPU）にて学習/推論コードを実施。

• ルール:

基準点：0.7　※コード脳死で回すだけでは超えられない

　１Google Colabで実行可能なモデル・実装であること

　２評価は StructEval（Text）のみを使用

　３提出物は推論結果JSONとHugging Face上のモデルURL

　４運営指定モデル・データのみ使用可

　５Omnicampusに提出すると自動採点・順位付け

＜demimomi-max44-qwen3-4b-dpo-qwen-cot-merged（ 0.70044点版）＞

model

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: 2
• Learning rate: 1e-06
• Beta: 0.05
• Max sequence length: 1536
• 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 = "demimomi/dpo-qwen-cot-merged"

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: [dpo_train_brushed_v4_balanced.json]
• License: MIT License. (As per dataset terms).
• Compliance: Users must follow the original base model's license terms.