Instructions to use sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged with Transformers:

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

pipe = pipeline("text-generation", model="sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged")
model = AutoModelForCausalLM.from_pretrained("sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged")
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

vLLM

How to use sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-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": "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged

SGLang

How to use sonodd/qwen3-4b-structeval-sft-v4-lr2e5-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 "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-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": "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-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 "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-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": "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged with Docker Model Runner:
```
docker model run hf.co/sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged
```

qwen3-4b-structeval-sft-v4-lr2e5-merged

SFT LoRA adapter (sonodd/qwen3-4b-structeval-sft-v4-lr2e5) をベースモデル (Qwen/Qwen3-4B-Instruct-2507) にマージしたフルモデルです。

用途

DPO ノートブックの DPO_BASE_MODEL に指定して SFT → DPO パイプライン を実行するために使用します。

# DPO ノートブック cell-10
os.environ["DPO_BASE_MODEL"]     = "sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged"
os.environ["DPO_SFT_ADAPTER_ID"] = ""  # マージ済みなので空

構成

Base model: Qwen/Qwen3-4B-Instruct-2507
SFT adapter: sonodd/qwen3-4b-structeval-sft-v4-lr2e5
Merge method: merge_and_unload() (float16)

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

F16

Model tree for sonodd/qwen3-4b-structeval-sft-v4-lr2e5-merged

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1705)

this model

Finetunes

2 models