Instructions to use qingy2024/GPT-OS3-V2-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qingy2024/GPT-OS3-V2-8B-Base with Transformers:

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

pipe = pipeline("text-generation", model="qingy2024/GPT-OS3-V2-8B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("qingy2024/GPT-OS3-V2-8B-Base")
model = AutoModelForCausalLM.from_pretrained("qingy2024/GPT-OS3-V2-8B-Base")
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 qingy2024/GPT-OS3-V2-8B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qingy2024/GPT-OS3-V2-8B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qingy2024/GPT-OS3-V2-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qingy2024/GPT-OS3-V2-8B-Base

SGLang

How to use qingy2024/GPT-OS3-V2-8B-Base 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 "qingy2024/GPT-OS3-V2-8B-Base" \
    --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": "qingy2024/GPT-OS3-V2-8B-Base",
		"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 "qingy2024/GPT-OS3-V2-8B-Base" \
        --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": "qingy2024/GPT-OS3-V2-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qingy2024/GPT-OS3-V2-8B-Base with Docker Model Runner:
```
docker model run hf.co/qingy2024/GPT-OS3-V2-8B-Base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GPT-OS3-V2-8B-Base

Still initialized from the pruned 8.4B/A3.6B GPT-OSS model but with a new chat template that lets you do:

>>> print(tokenizer.decode(tokenizer.apply_chat_template([
    {"role": "reasoning_effort", "content": "high"},
    {"role": "user", "content": "Write a Python function to calculate factorial"},
    {"role": "assistant", "content": "Here's a Python function to calculate factorial:"},
    {"role": "user", "content": "Write a Python function to calculate factorial"},
])))

=== OUTPUT ===
<|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-30

Reasoning: high

# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>user<|message|>Write a Python function to calculate factorial<|end|><|start|>assistant<|channel|>final<|message|>Here's a Python function to calculate factorial:<|end|><|start|>user<|message|>Write a Python function to calculate factorial<|end|>

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for qingy2024/GPT-OS3-V2-8B-Base

Finetunes

1 model

Quantizations

1 model