Instructions to use schroneko/qwen3-4b-sft-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schroneko/qwen3-4b-sft-v5 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "schroneko/qwen3-4b-sft-v5")

Transformers

How to use schroneko/qwen3-4b-sft-v5 with Transformers:

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

pipe = pipeline("text-generation", model="schroneko/qwen3-4b-sft-v5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("schroneko/qwen3-4b-sft-v5", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use schroneko/qwen3-4b-sft-v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schroneko/qwen3-4b-sft-v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schroneko/qwen3-4b-sft-v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schroneko/qwen3-4b-sft-v5

SGLang

How to use schroneko/qwen3-4b-sft-v5 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 "schroneko/qwen3-4b-sft-v5" \
    --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": "schroneko/qwen3-4b-sft-v5",
		"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 "schroneko/qwen3-4b-sft-v5" \
        --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": "schroneko/qwen3-4b-sft-v5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schroneko/qwen3-4b-sft-v5 with Docker Model Runner:
```
docker model run hf.co/schroneko/qwen3-4b-sft-v5
```

qwen3-4b-sft-v5

LoRA adapter for Qwen/Qwen3-4B-Instruct-2507, fine-tuned on structured output tasks (JSON, CSV, XML, YAML, TOML).

Training Details

Base model: Qwen/Qwen3-4B-Instruct-2507
Dataset: u-10bei/structured_data_with_cot_dataset_512_v5
LoRA rank: 64, alpha: 128, dropout: 0.0
Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Epochs: 3
Learning rate: 2e-5 (cosine scheduler, warmup 10%)
Batch size: 4, gradient accumulation: 4 (effective batch size: 16)
Max sequence length: 2048
Training precision: bf16
Loss masking: assistant-only with CoT masking (Output: marker)

Training Results

Total steps: 810
Final training loss: 0.37 (from 2.49)
Training time: ~113 minutes on NVIDIA GB10 (DGX Spark)

Hardware

NVIDIA DGX Spark (ARM64)
GPU: NVIDIA GB10 (sm_121, Blackwell)
VRAM: 119.7 GB unified memory
PyTorch nightly (2.11.0.dev20260105+cu130)

Framework Versions

PEFT 0.18.1
Transformers (latest)
Accelerate (latest)

Downloads last month: 1

Model tree for schroneko/qwen3-4b-sft-v5

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5499)

this model