curl --request GET \
  --url https://serving.app.predibase.com/tenant_id/deployments/v2/llms/deployment_name/info

{
  "docker_label": "null",
  "max_batch_total_tokens": "32000",
  "max_best_of": "2",
  "max_concurrent_requests": "128",
  "max_input_length": "1024",
  "max_stop_sequences": "4",
  "max_total_tokens": "2048",
  "max_waiting_tokens": "20",
  "model_device_type": "cuda",
  "model_dtype": "torch.float16",
  "model_id": "bigscience/blomm-560m",
  "model_pipeline_tag": "lorax",
  "model_sha": "e985a63cdc139290c5f700ff1929f0b5942cced2",
  "sha": "null",
  "validation_workers": "2",
  "version": "0.5.0",
  "waiting_served_ratio": "1.2"
}