Hugging Face · Schema

Info

Properties

Name	Type	Description
model_id	string	Loaded model ID
model_sha	string	Model revision SHA
model_dtype	string	Model data type
model_device_type	string	Device type (cuda, cpu)
model_pipeline_tag	string	Pipeline task tag
max_concurrent_requests	integer
max_best_of	integer
max_stop_sequences	integer
max_input_length	integer	Maximum input token length
max_total_tokens	integer	Maximum total tokens (input + output)
waiting_served_ratio	number
max_batch_total_tokens	integer
max_waiting_tokens	integer
validation_workers	integer
max_client_batch_size	integer
version	string	TGI version
sha	string	TGI build SHA
docker_label	string	Docker image label

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/Info",
  "title": "Info",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "description": "Loaded model ID",
      "example": "500123"
    },
    "model_sha": {
      "type": "string",
      "description": "Model revision SHA",
      "example": "example_value"
    },
    "model_dtype": {
      "type": "string",
      "description": "Model data type",
      "enum": [
        "float16",
        "bfloat16",
        "float32"
      ],
      "example": "float16"
    },
    "model_device_type": {
      "type": "string",
      "description": "Device type (cuda, cpu)",
      "example": "example_value"
    },
    "model_pipeline_tag": {
      "type": "string",
      "description": "Pipeline task tag",
      "example": "example_value"
    },
    "max_concurrent_requests": {
      "type": "integer",
      "example": 10
    },
    "max_best_of": {
      "type": "integer",
      "example": 10
    },
    "max_stop_sequences": {
      "type": "integer",
      "example": 10
    },
    "max_input_length": {
      "type": "integer",
      "description": "Maximum input token length",
      "example": 10
    },
    "max_total_tokens": {
      "type": "integer",
      "description": "Maximum total tokens (input + output)",
      "example": 10
    },
    "waiting_served_ratio": {
      "type": "number",
      "example": 42.5
    },
    "max_batch_total_tokens": {
      "type": "integer",
      "example": 10
    },
    "max_waiting_tokens": {
      "type": "integer",
      "example": 10
    },
    "validation_workers": {
      "type": "integer",
      "example": 10
    },
    "max_client_batch_size": {
      "type": "integer",
      "example": 10
    },
    "version": {
      "type": "string",
      "description": "TGI version",
      "example": "example_value"
    },
    "sha": {
      "type": "string",
      "description": "TGI build SHA",
      "example": "example_value"
    },
    "docker_label": {
      "type": "string",
      "description": "Docker image label",
      "example": "example_value"
    }
  }
}