请问下载完32B模型 具体的调用步骤是什么呢？

[ydtno4]

[Peng-fei-Wang]

Hi @ydtno4 , thanks for your question!

Here are the general steps to use our 32B model:

1. Deploy the Model: We recommend deploying the model using a high-performance inference framework like vLLM or SGLang. These tools will wrap the model into a standard API endpoint.

2. Call the API with Our Prompt: Once the model is deployed, you can call the API for inference using the specific prompt format we provide in our model page.