Instructions to use tenyyprn/qwen3-4b-structeval-exp15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tenyyprn/qwen3-4b-structeval-exp15 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, "tenyyprn/qwen3-4b-structeval-exp15")

Transformers

How to use tenyyprn/qwen3-4b-structeval-exp15 with Transformers:

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

pipe = pipeline("text-generation", model="tenyyprn/qwen3-4b-structeval-exp15")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tenyyprn/qwen3-4b-structeval-exp15", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tenyyprn/qwen3-4b-structeval-exp15 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tenyyprn/qwen3-4b-structeval-exp15"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tenyyprn/qwen3-4b-structeval-exp15",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tenyyprn/qwen3-4b-structeval-exp15

SGLang

How to use tenyyprn/qwen3-4b-structeval-exp15 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 "tenyyprn/qwen3-4b-structeval-exp15" \
    --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": "tenyyprn/qwen3-4b-structeval-exp15",
		"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 "tenyyprn/qwen3-4b-structeval-exp15" \
        --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": "tenyyprn/qwen3-4b-structeval-exp15",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tenyyprn/qwen3-4b-structeval-exp15 with Docker Model Runner:
```
docker model run hf.co/tenyyprn/qwen3-4b-structeval-exp15
```

Qwen3-4B StructEval Exp15 (CSV Fix)

Exp13 (SFT+DPO) をベースに、CSV変換の問題を修正するための特化LoRAアダプター。

Overview

Item	Detail
Base Model	Qwen/Qwen3-4B-Instruct-2507
Parent Adapter	Exp13 (SFT + DPO, merged)
Purpose	CSV出力の「starting with header row」誤解釈を修正
Method	Merged Exp13 + 追加LoRA fine-tuning

Training Details

Strategy

Exp13 DPOアダプターをベースモデルにマージ
マージ後のモデルに対して、CSV修正用の小規模LoRAを追加学習

Hyperparameters

Parameter	Value
Learning Rate	5e-5
Epochs	15
Batch Size	1
Gradient Accumulation	1
LoRA r	8
LoRA alpha	16
LoRA dropout	0.05
Target Modules	q/k/v/o_proj, gate/up/down_proj
Precision	fp16
Max Sequence Length	2048
Optimizer	AdamW
Seed	3407

Training Data

CSV修正用データセット（6サンプル）
「starting with header row」を正しく解釈し、ヘッダー+データ行を出力する学習

Hardware

NVIDIA DGX Spark (GB10 Blackwell GPU)
CUDA 12.1

Inference

System Prompt

You are a structured data expert. Output the requested format directly without any explanation, preamble, or markdown code blocks. Do not write ```json, ```yaml, ```toml, ```xml, ```csv or similar. Output only the raw structured data.

Settings

Parameter	Value
Temperature	1e-7 (near-greedy)
Max New Tokens	4096
do_sample	False

Usage

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

base_model_id = "Qwen/Qwen3-4B-Instruct-2507"
adapter_id = "tenyyprn/qwen3-4b-structeval-exp15"

tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(model, adapter_id)
model = model.merge_and_unload()
model.eval()

Results

Ensemble (Exp13 + Exp15) の公式コンペスコア: 0.781733

Exp15 単体ローカル評価

Format	Score
JSON	High
YAML	High
XML	High
CSV	Improved (fix applied)
TOML	Challenging

Related Models

Base: Qwen/Qwen3-4B-Instruct-2507
Parent (Exp13 DPO): SFT + DPO trained adapter (merged into this model)

License

Apache 2.0 (following base model license)

Downloads last month: 2

Model tree for tenyyprn/qwen3-4b-structeval-exp15

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5475)

this model