Generate
Generate completion endpoint which returns a response to a prompt.
Usage
curl -X GET 'http://127.0.0.1:5000/generate?prompt=write%20me%20a%20poem%20about%the%20ocean&stream=true'Example
Python
from mlxserver import MLXServer
server = MLXServer(model="mlx-community/Nous-Hermes-2-Mistral-7B-DPO-4bit-MLX")Curl
curl -X GET 'http://127.0.0.1:5000/generate?prompt=write%20me%20a%20poem%20about%the%20ocean&stream=true'Parameters
propmt (required) - The prompt you want to generate with.
stream - Stream the output. Default: False.