text-classification--distilbert-base-uncased-finetuned-sst-2-english.yaml

deployment_config:
  max_ongoing_requests: 1
  autoscaling_config:
    min_replicas: 1
    initial_replicas: 1
    max_replicas: 8
    target_ongoing_requests: 1.0
    metrics_interval_s: 10.0
    look_back_period_s: 30.0
    smoothing_factor: 1.0
    downscale_delay_s: 300.0
    upscale_delay_s: 90.0
  ray_actor_options:
    num_cpus: 0.1    # for a model deployment, we have 3 actor created, 1 and 2 will cost 0.1 cpu, and the model infrence will cost 6(see the setting in the end of the file)
model_conf:
  warmup: False
  model_task: text-classification
  model_id: distilbert-base-uncased-finetuned-sst-2-english
  max_input_words: 800
  initialization:
    initializer:
      type: SingleDevice
      dtype: float32
      from_pretrained_kwargs:
        trust_remote_code: true
    pipeline: defaulttransformers
scaling_config:
  num_workers: 1
  num_gpus_per_worker: 0
  num_cpus_per_worker: 6   # for infrence