Instructions to use yonetaro/qwen3-4b-structured-lora-v2-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yonetaro/qwen3-4b-structured-lora-v2-merged with Transformers:

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

pipe = pipeline("text-generation", model="yonetaro/qwen3-4b-structured-lora-v2-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yonetaro/qwen3-4b-structured-lora-v2-merged")
model = AutoModelForCausalLM.from_pretrained("yonetaro/qwen3-4b-structured-lora-v2-merged", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use yonetaro/qwen3-4b-structured-lora-v2-merged with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yonetaro/qwen3-4b-structured-lora-v2-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yonetaro/qwen3-4b-structured-lora-v2-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yonetaro/qwen3-4b-structured-lora-v2-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yonetaro/qwen3-4b-structured-lora-v2-merged

SGLang

How to use yonetaro/qwen3-4b-structured-lora-v2-merged 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 "yonetaro/qwen3-4b-structured-lora-v2-merged" \
    --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": "yonetaro/qwen3-4b-structured-lora-v2-merged",
		"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 "yonetaro/qwen3-4b-structured-lora-v2-merged" \
        --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": "yonetaro/qwen3-4b-structured-lora-v2-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use yonetaro/qwen3-4b-structured-lora-v2-merged with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yonetaro/qwen3-4b-structured-lora-v2-merged to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yonetaro/qwen3-4b-structured-lora-v2-merged to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for yonetaro/qwen3-4b-structured-lora-v2-merged to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="yonetaro/qwen3-4b-structured-lora-v2-merged",
    max_seq_length=2048,
)

Docker Model Runner
How to use yonetaro/qwen3-4b-structured-lora-v2-merged with Docker Model Runner:
```
docker model run hf.co/yonetaro/qwen3-4b-structured-lora-v2-merged
```

qwen3-4b-structured-output-lora-yk

This model is a LoRA adapter fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using Direct Preference Optimization (DPO) via the Unsloth library.

Training Objective

This adapter aligns responses with preferred outputs from the provided preference dataset.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: DPO (Direct Preference Optimization)
Epochs: 1
Learning rate: 2e-06
Beta: 0.1
Max sequence length: 768
LoRA Config: r=16, alpha=32

Usage (Adapter)

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

base_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "your_id/your-adapter-repo"

model = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter_id)

# Test inference
prompt = "Your question here"
tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)
inputs = tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

Sources & License (IMPORTANT)

Training Data: [u-10bei/dpo-dataset-qwen-cot]
License: MIT License. (As per dataset terms).
Compliance: Users must follow the original base model's license terms.

Downloads last month: 7

Safetensors

Model size

2B params

Tensor type

F32

F16

Model tree for yonetaro/qwen3-4b-structured-lora-v2-merged

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1875)

this model

yonetaro
/

qwen3-4b-structured-lora-v2-merged