Instructions to use NotoriousH2/Qwen3-4B-Countdown-RLVR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NotoriousH2/Qwen3-4B-Countdown-RLVR with Transformers:

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

pipe = pipeline("text-generation", model="NotoriousH2/Qwen3-4B-Countdown-RLVR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NotoriousH2/Qwen3-4B-Countdown-RLVR")
model = AutoModelForCausalLM.from_pretrained("NotoriousH2/Qwen3-4B-Countdown-RLVR", 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 NotoriousH2/Qwen3-4B-Countdown-RLVR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NotoriousH2/Qwen3-4B-Countdown-RLVR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NotoriousH2/Qwen3-4B-Countdown-RLVR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NotoriousH2/Qwen3-4B-Countdown-RLVR

SGLang

How to use NotoriousH2/Qwen3-4B-Countdown-RLVR 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 "NotoriousH2/Qwen3-4B-Countdown-RLVR" \
    --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": "NotoriousH2/Qwen3-4B-Countdown-RLVR",
		"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 "NotoriousH2/Qwen3-4B-Countdown-RLVR" \
        --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": "NotoriousH2/Qwen3-4B-Countdown-RLVR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NotoriousH2/Qwen3-4B-Countdown-RLVR with Docker Model Runner:
```
docker model run hf.co/NotoriousH2/Qwen3-4B-Countdown-RLVR
```

Qwen3-4B Countdown RLVR

이 모델은 Countdown 문제의 결정적 보상을 사용하여 Qwen3-4B를 GRPO로 학습한 병합 모델입니다. 숫자 4개를 각각 한 번 사용하고, 사칙연산으로 목표값을 만드는 수식을 생성합니다. 학습 데이터는 NotoriousH2/countdown-rlvr revision 257a0edd9e5ec3fed345c80d21d9c73d09995ecb를 사용했습니다.

1. 사용

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "NotoriousH2/Qwen3-4B-Countdown-RLVR"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

LoRA 파일과 토크나이저는 adapter/에 있습니다. 학습 설정은 training_config.json, 전체 학습 기록은 history.json에서 확인할 수 있습니다. 구간별 completion 길이와 체크포인트 재개 지점은 training_provenance.json에 있습니다.

검증 분할의 후보별 지표와 공개 체크포인트 선택 결과는 checkpoint_selection.json에 있습니다. 공개 병합 모델은 checkpoint-480을 사용합니다. 검증 평가는 서버 시드 42와 VLLM_BATCH_INVARIANT=1을 사용합니다. test 평가는 서버 시드 42와 VLLM_BATCH_INVARIANT=1을 사용합니다.