Downloads · 30 days
0
ryowatanabe240215/qwen3-4b-structured-output-lora_ver10-2_merge
qwen3-4b-structured-output-lora_ver10-2_merge is a text generation model from ryowatanabe240215. 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.
qwen3-4b-structured-output-loraver10-2merge
Downloads · 30 days
0
Access
Public
Updated Mar 2, 2026
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
qwen3-4b-structured-output-lora_ver10-2_merge
This repository provides a model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).
This model is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).
Loss is applied only to the final assistant output, while intermediate reasoning (Chain-of-Thought) is masked.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "ryowatanabe240215/qwen3-4b-structured-output-lora_ver10-2_merge"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
device_map="auto",
)
Training data: u-10bei/structured_data_with_cot_dataset_512_v2
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.