Instructions to use spade-rl/SPADE-Qwen3-4B-Games with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spade-rl/SPADE-Qwen3-4B-Games with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spade-rl/SPADE-Qwen3-4B-Games")
model = AutoModelForCausalLM.from_pretrained("spade-rl/SPADE-Qwen3-4B-Games", 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 spade-rl/SPADE-Qwen3-4B-Games with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/spade-rl/SPADE-Qwen3-4B-Games

SGLang

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

Docker Model Runner
How to use spade-rl/SPADE-Qwen3-4B-Games with Docker Model Runner:
```
docker model run hf.co/spade-rl/SPADE-Qwen3-4B-Games
```

SPADE-Qwen3-4B-Games

SPADE checkpoint for the games setting, trained from Qwen/Qwen3-4B-Instruct-2507.

SPADE trains a single model in two roles: an Environment Designer that writes executable environments, and a Reasoning Agent that solves them. The Designer is rewarded for producing environments at the frontier of what the Agent can currently solve, so the curriculum keeps pace with the policy instead of being fixed in advance. See the paper for details.


Base model	`Qwen/Qwen3-4B-Instruct-2507`
Setting	games
Context length	262,144

Quickstart

We advise you to use the latest version of transformers.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "spade-rl/SPADE-Qwen3-4B-Games"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Give me a short introduction to large language model."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=16384)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
print(tokenizer.decode(output_ids, skip_special_tokens=True))

Deployment

For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.5 to create an OpenAI-compatible API endpoint:

SGLang:

python -m sglang.launch_server --model-path spade-rl/SPADE-Qwen3-4B-Games --context-length 262144

vLLM:

vllm serve spade-rl/SPADE-Qwen3-4B-Games --max-model-len 262144

Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as 32,768.

Best practices

We recommend temperature=0.7, top_p=0.8, top_k=20, min_p=0, following the sampling guidance on the base model card.

Related artifacts

Grounding corpora: games | tool use
All SPADE models, data and generated environments: huggingface.co/spade-rl

Downloads last month: 770

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for spade-rl/SPADE-Qwen3-4B-Games

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1953)

this model

Collection including spade-rl/SPADE-Qwen3-4B-Games

SPADE Checkpoints

Collection

The six SPADE models: Qwen3 4B, 8B, and 30B-A3B, each trained on games and on tool use. • 6 items • Updated 7 days ago • 1

Paper for spade-rl/SPADE-Qwen3-4B-Games

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published 8 days ago • 51