Instructions to use WindyLab/Qwen3-0.6B-cybertown-RLVR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WindyLab/Qwen3-0.6B-cybertown-RLVR with Transformers:

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

pipe = pipeline("text-generation", model="WindyLab/Qwen3-0.6B-cybertown-RLVR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WindyLab/Qwen3-0.6B-cybertown-RLVR")
model = AutoModelForCausalLM.from_pretrained("WindyLab/Qwen3-0.6B-cybertown-RLVR")
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 WindyLab/Qwen3-0.6B-cybertown-RLVR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WindyLab/Qwen3-0.6B-cybertown-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": "WindyLab/Qwen3-0.6B-cybertown-RLVR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WindyLab/Qwen3-0.6B-cybertown-RLVR

SGLang

How to use WindyLab/Qwen3-0.6B-cybertown-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 "WindyLab/Qwen3-0.6B-cybertown-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": "WindyLab/Qwen3-0.6B-cybertown-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 "WindyLab/Qwen3-0.6B-cybertown-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": "WindyLab/Qwen3-0.6B-cybertown-RLVR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WindyLab/Qwen3-0.6B-cybertown-RLVR with Docker Model Runner:
```
docker model run hf.co/WindyLab/Qwen3-0.6B-cybertown-RLVR
```

Qwen3-0.6B-cybertown-RLVR

This model is a Cybertown RLVR checkpoint trained from the Cybertown SFT model.

The checkpoint corresponds to the merged bf16 model from RLVR step 300. It is packaged as a standard HuggingFace model directory and can be loaded directly with Transformers or served with vLLM.

RLVR Training Data Distribution

The RLVR training split contains 9,633 examples and only uses 6 task types.

Train Goal Types

train goal_type	count	ratio in train
assembly	3917	40.7%
transport	2522	26.2%
emergency_response	1727	17.9%
guidance	592	6.1%
traffic_enforcement	491	5.1%
target_following	384	4.0%

Train Initial/Replan

source	count	ratio
initial	2890	30.0%
replan	6743	70.0%

The validation split contains 1,700 examples, covering 10 task types with 170 examples per task type.

Intended Use

This model is intended for Cybertown semantic task planning and replanning evaluation under validator-based reward settings.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "WindyLab/Qwen3-0.6B-cybertown-RLVR"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

Downloads last month: 16

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for WindyLab/Qwen3-0.6B-cybertown-RLVR

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

WindyLab/Qwen3-0.6B-cybertown-SFT

Finetuned

(1)

this model

WindyLab
/

Qwen3-0.6B-cybertown-RLVR

Qwen3-0.6B-cybertown-RLVR

RLVR Training Data Distribution

Train Goal Types

Train Initial/Replan

Intended Use

Loading

Model tree for WindyLab/Qwen3-0.6B-cybertown-RLVR

Dataset used to train WindyLab/Qwen3-0.6B-cybertown-RLVR