Instructions to use spade-rl/SPADE-Qwen3-8B-Games with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spade-rl/SPADE-Qwen3-8B-Games with Transformers:

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

pipe = pipeline("text-generation", model="spade-rl/SPADE-Qwen3-8B-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-Qwen3-8B-Games")
model = AutoModelForCausalLM.from_pretrained("spade-rl/SPADE-Qwen3-8B-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-Qwen3-8B-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-Qwen3-8B-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-Qwen3-8B-Games",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spade-rl/SPADE-Qwen3-8B-Games

SGLang

How to use spade-rl/SPADE-Qwen3-8B-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-Qwen3-8B-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-Qwen3-8B-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-Qwen3-8B-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-Qwen3-8B-Games",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use spade-rl/SPADE-Qwen3-8B-Games with Docker Model Runner:
```
docker model run hf.co/spade-rl/SPADE-Qwen3-8B-Games
```

SPADE-Qwen3-8B-Games

SPADE checkpoint for the games setting, trained from Qwen/Qwen3-8B.

SPADE trains a single model in two roles: as a proposer that writes executable environments, and as an actor that plays them. The proposer is rewarded for producing environments at the frontier of what the actor can currently solve, so the curriculum keeps pace with the policy instead of being fixed in advance.


Base model	`Qwen/Qwen3-8B`
Setting	`games`
Released checkpoint	`iter399`
Grounding corpus	`spare-rl/spade-grounding-corpus-games-15k`

Environments. Environments generated online by the model itself, grounded on the 15k games corpus.

Checkpoint selection. Final checkpoint of the run (no offline eval sweep was run for this arm).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "spare-rl/SPADE-Qwen3-8B-Games"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")