Instructions to use n4/Qwen3-4B-Instruct-2507-sft_166 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use n4/Qwen3-4B-Instruct-2507-sft_166 with Transformers:

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

pipe = pipeline("text-generation", model="n4/Qwen3-4B-Instruct-2507-sft_166")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("n4/Qwen3-4B-Instruct-2507-sft_166")
model = AutoModelForCausalLM.from_pretrained("n4/Qwen3-4B-Instruct-2507-sft_166")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use n4/Qwen3-4B-Instruct-2507-sft_166 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "n4/Qwen3-4B-Instruct-2507-sft_166"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "n4/Qwen3-4B-Instruct-2507-sft_166",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/n4/Qwen3-4B-Instruct-2507-sft_166

SGLang

How to use n4/Qwen3-4B-Instruct-2507-sft_166 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 "n4/Qwen3-4B-Instruct-2507-sft_166" \
    --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": "n4/Qwen3-4B-Instruct-2507-sft_166",
		"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 "n4/Qwen3-4B-Instruct-2507-sft_166" \
        --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": "n4/Qwen3-4B-Instruct-2507-sft_166",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use n4/Qwen3-4B-Instruct-2507-sft_166 with Docker Model Runner:
```
docker model run hf.co/n4/Qwen3-4B-Instruct-2507-sft_166
```

Qwen3-4B-Instruct-2507-sft_166 (merged LoRA, multi-stage SFT)

This repository provides a merged full model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA.

Important: This repository does NOT provide separate LoRA adapter weights. It contains merged model weights only (the adapter is not uploaded).

Training Objective

This model is fine-tuned to improve structured output accuracy (JSON / YAML / XML / TOML / CSV).

Note:

This README focuses on the competition-required model card structure.
If you need more training/implementation details, please refer to your training logs or scripts.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: LoRA (adapters merged after training)
Max sequence length: 512
Epochs: 2
LoRA: r=1, alpha=2

Multi-stage SFT (2 stages)

Stage 1 (YAML-focused SFT)

Data: “to YAML” subset only (from the sources listed below)
Learning rate: 2.0e-4

Stage 2 (XML-focused SFT)

Data: “to XML” subset only (from the sources listed below)
Learning rate: 1.1e-4

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "n4/Qwen3-4B-Instruct-2507-sft_166"
tok = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto", trust_remote_code=True)

user_query = "Please output the following information in JSON format: Name=naisy, Age=714"
messages = [{"role": "user", "content": user_query}]
prompt = tok.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
gen_ids = out[0][inputs["input_ids"].shape[1]:]
text = tok.decode(gen_ids, skip_special_tokens=True)
print(text)

Sources & Terms (IMPORTANT)

Training data:

u-10bei/structured_data_with_cot_dataset_512_v5
daichira/structured-5k-mix-sft

Dataset License:

u-10bei/structured_data_with_cot_dataset_512_v5: MIT License
daichira/structured-5k-mix-sft: CC-BY-4.0

Compliance: Users must comply with:

the dataset licenses above (including attribution requirements for CC-BY-4.0), and
the base model's original terms of use (apache-2.0).

Limitations

Structured outputs may still fail under very long, deeply nested, or ambiguous schemas.
Validate outputs (e.g., JSON parse / XML validation) in downstream use cases.

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for n4/Qwen3-4B-Instruct-2507-sft_166

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5501)

this model

n4
/

Qwen3-4B-Instruct-2507-sft_166