Downloads · 30 days
5
2% of all-time downloads
tussiiiii/qwen3-4b-structured-output-lora-continued-v5-daichira-ver3-2
qwen3-4b-structured-output-lora-continued-v5-daichira-ver3-2 is a text generation model from tussiiiii. 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-lora-continued-v5-daichira-ver3-2
Downloads · 30 days
5
2% of all-time downloads
All-time downloads
228
Public
Repo size
540 MB
Likes
0
Public
Click a slice to open those files.
.safetensors529 MB · 97%
From the Hugging Face model README
qwen3-4b-structured-output-lora-continued-v5-daichira-ver3-2
A LoRA adapter specialized for structured output generation (JSON / YAML / XML / TOML / CSV) in long-input settings.
This repository provides a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using QLoRA (4-bit, Unsloth).
This adapter was trained in four stages using LoRA continuation: structured_data_with_cot_dataset_512_v2 (initial fine-tuning) → structured_data_with_cot_dataset_512_v5 (continued fine-tuning) → structured-5k-mix-sft (continued fine-tuning) → structured-hard-sft-4k (continued fine-tuning).
This repository contains LoRA adapter weights only. The base model must be loaded separately.
This adapter is trained to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).
Loss is applied only to the final assistant output. When output markers are present, intermediate reasoning (Chain-of-Thought) is masked.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "your_id/your-repo"
tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
base,
torch_dtype=torch.float16,
device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)
The following licenses apply to the training datasets used in this repository:
u-10bei structured_data_with_cot_dataset family
(e.g., structured_data_with_cot_dataset_512_v2, v4, v5, etc.):
Licensed under the MIT License.
Use of these datasets is permitted under the terms of the MIT License, provided that the copyright notice is retained.
daichira structured_ SFT datasets*
(structured-5k-mix-sft, structured-hard-sft-4k):
Licensed under the Creative Commons Attribution 4.0 International (CC-BY-4.0) license.
This license permits use, modification, and redistribution, including for commercial purposes, provided that appropriate attribution is given.
Attribution: please credit the original dataset authors (u-10bei, daichira) and link to the dataset pages when redistributing or publishing derived works.
Users must comply with:
This repository distributes LoRA adapter weights only and does not redistribute the original datasets.