Instructions to use burtenshaw/Qwen3-30B-A3B-python-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use burtenshaw/Qwen3-30B-A3B-python-coder with Transformers:

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

pipe = pipeline("text-generation", model="burtenshaw/Qwen3-30B-A3B-python-coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("burtenshaw/Qwen3-30B-A3B-python-coder")
model = AutoModelForCausalLM.from_pretrained("burtenshaw/Qwen3-30B-A3B-python-coder")
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

vLLM

How to use burtenshaw/Qwen3-30B-A3B-python-coder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/burtenshaw/Qwen3-30B-A3B-python-coder

SGLang

How to use burtenshaw/Qwen3-30B-A3B-python-coder 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 "burtenshaw/Qwen3-30B-A3B-python-coder" \
    --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": "burtenshaw/Qwen3-30B-A3B-python-coder",
		"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 "burtenshaw/Qwen3-30B-A3B-python-coder" \
        --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": "burtenshaw/Qwen3-30B-A3B-python-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use burtenshaw/Qwen3-30B-A3B-python-coder with Docker Model Runner:
```
docker model run hf.co/burtenshaw/Qwen3-30B-A3B-python-coder
```

burtenshaw HF Staff commited on May 5, 2025

Commit

bce8c2b

verified ·

1 Parent(s): 3762bfb

Upload train.py with huggingface_hub

Browse files

Files changed (1) hide show

train.py +1 -1

train.py CHANGED Viewed

@@ -122,6 +122,7 @@ training_args = SFTConfig(
     fp16=False,
     max_steps=1000,
     report_to="wandb",  # Disable reporting to avoid wandb prompts
 )
 """## Initialize and run the SFT Trainer"""
@@ -134,7 +135,6 @@ trainer = SFTTrainer(
     eval_dataset=dataset["test"] if "test" in dataset else None,
     peft_config=peft_config,
     processing_class=tokenizer,
-    output_dir="./tmp/sft-model",
 )
 # Train the model

     fp16=False,
     max_steps=1000,
     report_to="wandb",  # Disable reporting to avoid wandb prompts
+    output_dir="./tmp/sft-model",
 )
 """## Initialize and run the SFT Trainer"""
     eval_dataset=dataset["test"] if "test" in dataset else None,
     peft_config=peft_config,
     processing_class=tokenizer,
 )
 # Train the model