Instructions to use shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800 with Transformers:

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

pipe = pipeline("text-generation", model="shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800")
model = AutoModelForCausalLM.from_pretrained("shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800", 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 shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800

SGLang

How to use shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800 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 "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800" \
    --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": "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800",
		"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 "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800" \
        --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": "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800 with Docker Model Runner:
```
docker model run hf.co/shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800
```

Qwen3-30B-A3B GRPO BF16 Control — Step 800

This is a research checkpoint derived from Qwen/Qwen3-30B-A3B-Base with group-relative policy optimization on mathematical reasoning data. It was exported at training step 800 from the BF16 control run.

The checkpoint is provided as standard BF16 Hugging Face safetensors and requires no custom inference code.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

Use transformers>=4.51.0 for Qwen3-MoE support.

Notes

This is an intermediate research checkpoint, not a production release. Users should independently evaluate correctness, safety, and suitability for their deployment setting. The base-model license applies.

Downloads last month: 36

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for shawnzzzzz/Qwen3-30B-A3B-GRPO-BF16-Control-Step800

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

(67)

this model