Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4

vllm serve tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4 --reasoning-parser qwen3

sglang serve --model-path tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4 --port 8000 --reasoning-parser qwen3

from openai import OpenAI
model_name = "tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4"
client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY"
)
result = client.chat.completions.create(
    model=model_name,
    messages=[
        {"role": "user", "content": "Create a casual one-day Tokyo itinerary in Japanese."}
    ],
    max_tokens=4096,
    temperature=0.6,
    top_p=0.95,
    extra_body={
        "top_k": 20,
        "min_p": 0,
    }
)
print("Reasoning:")
print(result.choices[0].message.reasoning)
print("
Response:")
print(result.choices[0].message.content)