Instructions to use shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730 with Transformers:

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

pipe = pipeline("text-generation", model="shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730")
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-DAPO-BF16-step-0730")
model = AutoModelForCausalLM.from_pretrained("shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730", 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-DAPO-BF16-step-0730 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-DAPO-BF16-step-0730"
# 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-DAPO-BF16-step-0730",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730

SGLang

How to use shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730 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-DAPO-BF16-step-0730" \
    --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-DAPO-BF16-step-0730",
		"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-DAPO-BF16-step-0730" \
        --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-DAPO-BF16-step-0730",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730 with Docker Model Runner:
```
docker model run hf.co/shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730
```

Qwen3-30B-A3B-DAPO-BF16-step-0730

This repository contains training checkpoint step 730, converted from a distributed training checkpoint into standard Hugging Face safetensors. It is part of the Qwen3-30B-A3B W4A4-QAT vs BF16 Checkpoints series.

Checkpoint metadata

Architecture: Qwen3MoeForCausalLM
Model type: qwen3_moe
Base model: Qwen/Qwen3-30B-A3B-Base
Training trajectory: BF16 baseline
Public trajectory label: BF16 baseline
Source checkpoint: global_step_730
Tensor storage: BF16
Matched counterpart: shawnzzzzz/Qwen3-30B-A3B-DAPO-FFN-W4A4-QAT-BF16Master-step-0730
Matched source step: 730
Absolute step difference: 0

Important quantization note

This is the BF16 baseline trajectory. QAT was disabled, and the repository contains standard BF16 Hugging Face weights.

Intended use

These checkpoints are research artifacts for comparing approximately step-matched W4A4-QAT and BF16 training trajectories. They have not been evaluated here as general-purpose production models.

Validation

The export was checked for:

required Hugging Face model and tokenizer metadata;
readable safetensors headers and complete shard index;
exact index-to-shard key consistency;
BF16 tensor dtype throughout;
exact key and tensor-shape match against the native Qwen3-MoE architecture;
full source-artifact content comparison against the validated export;
Hugging Face path, byte-size, LFS SHA256, and metadata-download integrity.

SHA256SUMS covers every published file in this repository except the checksum manifest itself. Internal execution provenance is intentionally omitted from this public release.

Downloads last month: 161

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

(62)

this model

Collection including shawnzzzzz/Qwen3-30B-A3B-DAPO-BF16-step-0730

Qwen3-30B-A3B W4A4-QAT vs BF16 Checkpoints

Collection

Seven step-matched Qwen3-30B-A3B DAPO pairs: FFN W4A4-QAT BF16 master weights (not packed W4A4) and a BF16 baseline. • 14 items • Updated Jul 12