Downloads · 30 days
0
ryo-llm/dpo-qwen3-4b-structured-output-202602071440
dpo-qwen3-4b-structured-output-202602071440 is a text generation model from ryo-llm. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO) via Unsloth.
Downloads · 30 days
0
Access
Public
Updated Feb 7, 2026
Repo size
144 MB
Likes
0
Public
Click a slice to open those files.
.safetensors132 MB · 89%
From the Hugging Face model README
This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO) via Unsloth.
This repository contains LoRA adapter weights.
DPO is used to reduce undesired verbosity and align outputs toward preferred structured responses.