Downloads · 30 days
9
2% of all-time downloads
satoyutaka/LLM2025_main_0_DPO7
LLM2025_main_0_DPO7 is a text generation model from satoyutaka. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository provides a LoRA adapter for Qwen/Qwen3-4B-Instruct-2507. It represents the v7 iteration of the "struct-eval-comp" series, maintaining the high-tier score of 0.77136 with enhanced formatting stability.
Downloads · 30 days
9
2% of all-time downloads
All-time downloads
383
Public
Repo size
144 MB
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 89%
From the Hugging Face model README
This repository provides a LoRA adapter for Qwen/Qwen3-4B-Instruct-2507. It represents the v7 iteration of the "struct-eval-comp" series, maintaining the high-tier score of 0.77136 with enhanced formatting stability.
This version was developed by performing specialized DPO (Direct Preference Optimization) on top of the v6 adapter, specifically targeting the stabilization of raw outputs over multiple training epochs.
The v7 adapter focuses on "Structural Persistence." Building on the logical foundations of v6, this version underwent extended training to further decouple the model's reasoning process (CoT) from its output format, ensuring that it provides deep analysis while strictly adhering to raw JSON/CSV/TOML formats without Markdown interference.
q_proj, v_proj, k_proj, o_proj, gate_proj, up_proj, down_proj)from unsloth import FastLanguageModel
import torch
base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "satoyutaka/LLM2025_main_0_DPO7"
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = base,
max_seq_length = 2048,
load_in_4bit = True,
)
model.load_adapter(adapter)
このリポジトリは、Qwen/Qwen3-4B-Instruct-2507 用のLoRAアダプターです。 struct-eval-comp プロジェクトにおける「V7」モデルであり、V6の最高スコア 0.77136 を維持しつつ、フォーマットの安定性を強化したモデルです。
V6アダプターをベースとし、複数エポックにわたるDPO(直接選好最適化)を施すことで、出力スタイルの定着を図っています。
V7の主な目的は「構造化の永続性」です。V6で培った高い論理性(CoT)を継承しつつ、さらに「思考は深く、出力は素っ気なく(Rawデータのみ)」という挙動を3エポックの学習で徹底させました。JSON / CSV / TOML 形式の抽出精度を保ちながら、Markdown等の装飾を徹底的に排除することに特化しています。
(英語セクションの Usage コードを参照してください。アダプターIDは satoyutaka/qwen3-4b-struct-evaluation-dpo-v7 に適宜読み替えてください)