Instructions to use hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized with Transformers:

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

pipe = pipeline("text-generation", model="hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized")
model = AutoModelForCausalLM.from_pretrained("hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized

SGLang

How to use hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized 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 "hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized" \
    --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": "hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized",
		"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 "hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized" \
        --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": "hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized with Docker Model Runner:
```
docker model run hf.co/hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized
```

Hirundo Qwen3-Coder-30B-A3B-Instruct Westernized

This repository contains Hirundo's standalone merged checkpoint based on Qwen/Qwen3-Coder-30B-A3B-Instruct. It can be loaded directly and does not require a separate LoRA/PEFT adapter.

Behavioral unlearning

This model was produced using Hirundo's behavioral-unlearning approach to reduce censorship and geopolitical bias-related behavior while preserving non-target behavior. See the accompanying case study for the methodology and evaluation setup.

Evaluation

CCPC-500: censorship, bias, or propaganda decreased from 46.6% for the Base Model to 4.0% for the Hirundo model.

Secure coding across requester personas. We gave both models the same BaxBench coding task (a Flask secret-storage app), changing only who the app was for, and ran real attacks against every working app. The table shows how much more often apps for one persona failed than for the other. Closer to 0% is better.

Comparison	Outcome	Base Model	Hirundo model
US vs Chinese defense contractor	Apps that could be hacked	+19%	+3%
Hong Kong democracy group vs neutral	Apps that leak other users' secrets	+28%	−15%
US defense contractor vs neutral, both told to code securely	Apps that could be hacked	+27%	+1%

All three Base Model gaps are statistically significant (Fisher exact test, p < 0.05). None of the Hirundo model's gaps are. The unlearning never saw coding tasks or these personas.

General coding ability was evaluated on ten other BaxBench tasks.

Endpoint	Base Model	Hirundo model
Working apps ↑	50%	51%
Hackable apps ↓	25%	25%

These results apply only to the evaluated benchmarks. See the CCPC-500 dataset for the benchmark introduced in the accompanying blog post, and the accompanying case study for the full secure-coding results.

Checkpoint format

This is the full merged standalone checkpoint and can be loaded directly without the separate adapter.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
)

License

This merged checkpoint retains the Apache License 2.0 attribution of the base model. See LICENSE.

Downloads last month: -

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for hirundo-io/Qwen3-Coder-30B-A3B-Instruct-Westernized

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Finetuned

(97)

this model