Instructions to use Pinkstack/DistilGPT-OSS-qwen3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/DistilGPT-OSS-qwen3-4B with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/DistilGPT-OSS-qwen3-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstack/DistilGPT-OSS-qwen3-4B")
model = AutoModelForCausalLM.from_pretrained("Pinkstack/DistilGPT-OSS-qwen3-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pinkstack/DistilGPT-OSS-qwen3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/DistilGPT-OSS-qwen3-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pinkstack/DistilGPT-OSS-qwen3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/DistilGPT-OSS-qwen3-4B

SGLang

How to use Pinkstack/DistilGPT-OSS-qwen3-4B 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 "Pinkstack/DistilGPT-OSS-qwen3-4B" \
    --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": "Pinkstack/DistilGPT-OSS-qwen3-4B",
		"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 "Pinkstack/DistilGPT-OSS-qwen3-4B" \
        --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": "Pinkstack/DistilGPT-OSS-qwen3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pinkstack/DistilGPT-OSS-qwen3-4B with Docker Model Runner:
```
docker model run hf.co/Pinkstack/DistilGPT-OSS-qwen3-4B
```

Pinkstack commited on Sep 19, 2025

Commit

f6f8725

verified ·

1 Parent(s): e36053f

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -0

README.md CHANGED Viewed

@@ -1,5 +1,50 @@
 ---
 license: apache-2.0
 ---
 ![Distil gpt oss logo](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/RxoOFH7vZmoyyKOUlB_oX.png)

 ---
 license: apache-2.0
+base_model:
+- Qwen/Qwen3-4B-Thinking-2507
+pipeline_tag: text-generation
+tags:
+- cot
+- code
+- gpt_oss
+- conversational
+- distillation
+- math
 ---
 ![Distil gpt oss logo](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/RxoOFH7vZmoyyKOUlB_oX.png)
+# What it is
+DistilGPT-OSS-qwen3-4B is a Qwen3 4B-2507 thinking fine tune, it supports up to **256K** tokens of input and output (aka total context) and can think for up to **65536** tokens when set to **high** reasoning effort. unlike the original qwen3, this model was fine-tuned on GPT-OSS reasoning outputs (unlike Deepseek r1 outputs which qwen3 was probably fine-tuned on for advanced reasoning). By fine-tuning on GPT-OSS outputs, the model was able to learn how to think efficiently, follow instructions better, and the new ability to think with a certain effort based on how much you want it to think.
+⚠️This model is NOT as censored as the original GPT-OSS, we focused on performance rather than censorship. The model is still safety trained, it would just allow for more *"creative"* prompts, unlike GPT-OSS. We are not responsible for what the model generates.
+Keep in mind, this is a community project and we are NOT related to qwen by Alibaba nor GPT-OSS by OpenAi.
+# Format
+This is the chat format of this model (you can also check the Jinja template file in "Files and versions"):
+```
+<|im_start|>system
+You are a helpful assistant
+Reasoning effort: low<|im_end|>
+<|im_start|>user
+Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,<|im_end|>
+<|im_start|>assistant
+<think>
+Just continue: 13,21,34,...
+</think>
+The Fibonacci sequence continues by adding the two preceding numbers.
+After **8** the next term is **13** (1 + 8 = 9 – 1 = 8 + 5 = 13), then **21** (8 + 13 = 21), followed by **34** (13 + 21 = 34), and so on.
+So the sequence starts:
+**1, 1, 2, 3, 5, 8, 13, 21, 34, …**<|im_end|>
+```
+As you can see, you set the reasoning effort via the system prompt. We recommend going **2** lines down and only then putting "Reasoning effort: [low,medium,high]. For your information that output was generated by our model.
+# Additional information
+The model was trained using unsloth, using a mix of private datasets and public datasets.