Instructions to use OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329 with Transformers:

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

pipe = pipeline("text-generation", model="OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329")
model = AutoModelForCausalLM.from_pretrained("OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329

SGLang

How to use OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329 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 "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329" \
    --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": "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329",
		"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 "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329" \
        --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": "OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329 with Docker Model Runner:
```
docker model run hf.co/OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329
```

概要

DataPilot/Knowledge-QA-SingleTurn-DatasetでSFTし，日本語の入力に対し日本語で思考するようにしたモデルです．コンテキスト長は16384です．

使い方

from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer

tokenizer = AutoTokenizer.from_pretrained("OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329")
model = AutoModelForCausalLM.from_pretrained("OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329", dtype="auto", device_map="auto")
messages = [
    {"role": "user", "content": "肉じゃがの作り方を教えて"},
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

outputs = model.generate(
    **inputs, 
    max_new_tokens=5000, 
    do_sample=True,
    temperature=0.7,
    top_p=0.8,
    top_k=20,
    streamer=streamer,              
)

Uploaded finetuned model

Developed by: OsakanaTeishoku
License: apache-2.0
Finetuned from model : unsloth/Qwen3-4B-Thinking-2507

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

unsloth/Qwen3-4B-Thinking-2507

Finetuned

(107)

this model

OsakanaTeishoku
/

Qwen3-4B-Thinking-2507-reasoning-ja-20260329

概要

使い方

Uploaded finetuned model

Model tree for OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329

Dataset used to train OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329