Cerebras Inference

Cerebras Inference uses specialized silicon to provides fast inference.

1. Create an account in the portal here.
2. Create and copy the API key for use in Continue.
3. Update your Continue config file:

YAML

Package or config.yaml

models:
  - name: Cerebras Llama 3.1 70B
    provider: cerebras
    model: llama3.1-70b
    apiKey:  <YOUR_CEREBRAS_API_KEY>

JSON

config.json

{
  "models": [
    {
      "title": "Cerebras Llama 3.1 70B",
      "provider": "cerebras",
      "model": "llama3.1-70b",
      "apiKey": "<YOUR_CEREBRAS_API_KEY>"
    }
  ]
}