Instructions to use WeiboAI/VibeThinker-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WeiboAI/VibeThinker-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="WeiboAI/VibeThinker-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WeiboAI/VibeThinker-1.5B")
model = AutoModelForCausalLM.from_pretrained("WeiboAI/VibeThinker-1.5B")
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

vLLM

How to use WeiboAI/VibeThinker-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WeiboAI/VibeThinker-1.5B"
# 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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WeiboAI/VibeThinker-1.5B

SGLang

How to use WeiboAI/VibeThinker-1.5B 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-1.5B" \
    --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-1.5B",
		"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-1.5B" \
        --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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WeiboAI/VibeThinker-1.5B with Docker Model Runner:
```
docker model run hf.co/WeiboAI/VibeThinker-1.5B
```

hello? 虽然是一个推理模型，但有的方面也太离谱了吧

by yu0226 - opened Nov 20, 2025

Discussion

yu0226

Nov 20, 2025

•

edited Nov 20, 2025

我可以接受一个模型专门用于math和coding，但一个最简单的hello都输出了一串数学解答，是不是太离谱了呢？希望作者可以解释一下这个现象

yu0226 changed discussion status to closed Nov 20, 2025

yu0226 changed discussion status to open Nov 20, 2025

n1cck

Nov 20, 2025

明显过拟合了

YinZhiBin

WeiboAI org Nov 20, 2025

Our model is an experimental research prototype dedicated to mathematical reasoning, released specifically to validate the claims in our paper. It relies on a math-only base model with further post-training focused on math and code. Consequently, it has not been aligned for general conversational capabilities. We do not recommend using this model for general chat, as it is biased towards responding from a problem-solving perspective. Additionally, please note that running inference with quantized versions may lead to increased hallucinations when testing general conversation scenarios.