Instructions to use p-e-w/Qwen3-4B-Instruct-2507-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use p-e-w/Qwen3-4B-Instruct-2507-heretic with Transformers:

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

pipe = pipeline("text-generation", model="p-e-w/Qwen3-4B-Instruct-2507-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("p-e-w/Qwen3-4B-Instruct-2507-heretic")
model = AutoModelForCausalLM.from_pretrained("p-e-w/Qwen3-4B-Instruct-2507-heretic")
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 p-e-w/Qwen3-4B-Instruct-2507-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "p-e-w/Qwen3-4B-Instruct-2507-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "p-e-w/Qwen3-4B-Instruct-2507-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/p-e-w/Qwen3-4B-Instruct-2507-heretic

SGLang

How to use p-e-w/Qwen3-4B-Instruct-2507-heretic 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 "p-e-w/Qwen3-4B-Instruct-2507-heretic" \
    --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": "p-e-w/Qwen3-4B-Instruct-2507-heretic",
		"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 "p-e-w/Qwen3-4B-Instruct-2507-heretic" \
        --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": "p-e-w/Qwen3-4B-Instruct-2507-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use p-e-w/Qwen3-4B-Instruct-2507-heretic with Docker Model Runner:
```
docker model run hf.co/p-e-w/Qwen3-4B-Instruct-2507-heretic
```

flags and values to pass to reproduce this result?

by bird0867 - opened Nov 19, 2025

Discussion

bird0867

Nov 19, 2025

How long did you end up searching for this result and would you credit or recommend any particular flags to be passed? Have you noticed any trends that would be surprising to someone whose used previous methods?

P.S. Congrats and thank you for this work!

bird0867

Nov 19, 2025

•

edited Nov 19, 2025

For anyone who finds this, I got a lucky result after about 500 tries, just up your tries.

Thank you again, this is wonderful stuff.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment