Instructions to use WeiboAI/VibeThinker-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WeiboAI/VibeThinker-3B with Transformers:

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

pipe = pipeline("text-generation", model="WeiboAI/VibeThinker-3B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WeiboAI/VibeThinker-3B")
model = AutoModelForCausalLM.from_pretrained("WeiboAI/VibeThinker-3B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WeiboAI/VibeThinker-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WeiboAI/VibeThinker-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WeiboAI/VibeThinker-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WeiboAI/VibeThinker-3B

SGLang

How to use WeiboAI/VibeThinker-3B 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 "WeiboAI/VibeThinker-3B" \
    --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": "WeiboAI/VibeThinker-3B",
		"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 "WeiboAI/VibeThinker-3B" \
        --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": "WeiboAI/VibeThinker-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WeiboAI/VibeThinker-3B with Docker Model Runner:
```
docker model run hf.co/WeiboAI/VibeThinker-3B
```

YinZhiBin commited on Jun 17

Commit

f148e22

verified ·

1 Parent(s): 0c7115f

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -16,6 +16,11 @@ library_name: transformers
 # VibeThinker-3B
 <p align="center"><a href="https://github.com/WeiboAI/VibeThinker">GitHub</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://modelscope.cn/models/WeiboAI/VibeThinker-3B">ModelScope</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://huggingface.co/papers/2606.16140">Technical Report</a></p>
 ## Introduction

 # VibeThinker-3B
+<blockquote style="border-left: 4px solid #ff6b6b; background-color: #fff5f5; padding: 10px 15px; margin: 10px 0; color: #cc3333;">
+    <span style="font-weight: bold;">🚨 </span>**Model Purpose and Recommended Usage**: This model is not intended to be a general‑purpose model that competes with large, state‑of-the‑art systems. Instead, it is designed to explore how far small models can go on specific reasoning‑intensive tasks, and to share our perspective with the community. Accordingly, we trained it only on data that reflect core reasoning abilities: competitive programming problems (e.g., LeetCode‑style) and mathematical/logical reasoning.
+**Important Note**: This model was not trained on tool‑calling or agent‑based programming data. We therefore do not recommend using it for function calling, API orchestration, or autonomous coding agents.
+</blockquote>
 <p align="center"><a href="https://github.com/WeiboAI/VibeThinker">GitHub</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://modelscope.cn/models/WeiboAI/VibeThinker-3B">ModelScope</a>&nbsp;&nbsp;|&nbsp;&nbsp;<a href="https://huggingface.co/papers/2606.16140">Technical Report</a></p>
 ## Introduction