Instructions to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("azuki-digital/qwen3-4b-struct-lora-v4-merged")
model = PeftModel.from_pretrained(base_model, "azuki-digital/qwen3-4b-struct-lora-v11-adapter")

Transformers

How to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="azuki-digital/qwen3-4b-struct-lora-v11-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("azuki-digital/qwen3-4b-struct-lora-v11-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "azuki-digital/qwen3-4b-struct-lora-v11-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azuki-digital/qwen3-4b-struct-lora-v11-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/azuki-digital/qwen3-4b-struct-lora-v11-adapter

SGLang

How to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "azuki-digital/qwen3-4b-struct-lora-v11-adapter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azuki-digital/qwen3-4b-struct-lora-v11-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "azuki-digital/qwen3-4b-struct-lora-v11-adapter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "azuki-digital/qwen3-4b-struct-lora-v11-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use azuki-digital/qwen3-4b-struct-lora-v11-adapter with Docker Model Runner:
```
docker model run hf.co/azuki-digital/qwen3-4b-struct-lora-v11-adapter
```

qwen3-4b-struct-lora-v11

This repository provides a LoRA adapter fine-tuned on top of:

azuki-digital/qwen3-4b-struct-lora-v4-merged

⚠️ This repository contains LoRA adapter weights only.
The base model must be loaded separately.

Training Objective

This adapter 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.

Training Configuration

Item	Value
Base model	azuki-digital/qwen3-4b-struct-lora-v4-merged
Method	LoRA SFT (no quantization, bf16)
Max sequence length	4096
Epochs	2
Learning rate	1e-5
Warmup ratio	0.05
Weight decay	0.05
LoRA r	32
LoRA alpha	64
LoRA dropout	0.05
Target modules	q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
Mask CoT	Yes (`after_marker`)
Dataset	daichira/structured-3k-mix-sft

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = "azuki-digital/qwen3-4b-struct-lora-v4-merged"
adapter = "azuki-digital/qwen3-4b-struct-lora-v11"

tokenizer = AutoTokenizer.from_pretrained(base)

model = AutoModelForCausalLM.from_pretrained(
    base,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

model = PeftModel.from_pretrained(model, adapter)

Sources & License (IMPORTANT)

Training Data • daichira/structured-3k-mix-sft • License: CC-BY-4.0

This dataset is used under the terms of CC-BY-4.0.

Compliance

Users must comply with: 1. Dataset attribution requirements (CC-BY-4.0) 2. Base model license (Apache-2.0) 3. This repository license (Apache-2.0)

Downloads last month: 8

Model tree for azuki-digital/qwen3-4b-struct-lora-v11-adapter

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

azuki-digital/qwen3-4b-struct-lora-v4-merged

Adapter

(1)

this model

azuki-digital
/

qwen3-4b-struct-lora-v11-adapter