Text Generation
Transformers
Safetensors
English
qwen2
math
code
reasoning
gpqa
instruction-following
conversational
Eval Results
text-generation-inference
Instructions to use WeiboAI/VibeThinker-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("WeiboAI/VibeThinker-3B") model = AutoModelForMultimodalLM.from_pretrained("WeiboAI/VibeThinker-3B") 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
Add evaluation results from model card benchmark tables
#21 opened about 5 hours ago
by
SaylorTwift
Really looking forward for 9B or 12B variants
1
#20 opened about 5 hours ago
by
perelmanych
Colab notebook generated by "Use this model" fails with HF Router
1
#19 opened about 11 hours ago
by
OMCHOKSI108
Brain atlas comparison of 1B and 3B VibeThinker models.
👍 2
2
#18 opened about 24 hours ago
by
juiceb0xc0de
very sensitive to quantization
#17 opened 1 day ago
by
J22
I Apologize on Behalf of Humanity
❤️👍 13
3
#16 opened 3 days ago
by
fernicar
Will data be open sourced?
👍 1
2
#15 opened 3 days ago
by
Sourajit123
mtp draft model
#14 opened 4 days ago
by
erichartford
怎么自我认知还是deepseek?而且好像没有做快慢思考,无法自适应控制思考长度
3
#12 opened 6 days ago
by
user48271
A masterpiece
3
#11 opened 6 days ago
by
pgib2003
some benchmark results for ZebraLogic
👍 2
2
#10 opened 6 days ago
by
khanh2023
后续会不会有更大参数规模的模型发布?
1
#9 opened 6 days ago
by
cmy2019
这不是套壳的qwen 2 3B吗?
👍 1
1
#8 opened 6 days ago
by
cloudyu
It's a very strong model for what it is trained! Bravo!
❤️ 2
1
#7 opened 6 days ago
by
codingquark-personal
Thought process Bug In LM-Studio
2
#6 opened 7 days ago
by
Priderock
这模型几乎通过了我所有的本地推理测试,很强,唯一做不出来的问题我贴在下面
❤️ 1
6
#5 opened 7 days ago
by
pypry
Installation Video and Testing - Step by Step
👍❤️ 2
1
#4 opened 7 days ago
by
fahdmirzac
I tested this model
❤️ 4
5
#3 opened 7 days ago
by
dpe1
Has anyone tried this
3
#2 opened 7 days ago
by
dpe1
Don't Be Lazy
2
#1 opened 8 days ago
by
usermma