@huggingface/tasks 0.13.1-test → 0.13.1-test2

package/src/tasks/text-generation/inference.ts

@@ -0,0 +1,200 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+
+/**
+ * Text Generation Input.
+ *
+ * Auto-generated from TGI specs.
+ * For more details, check out
+ * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
+ */
+export interface TextGenerationInput {
+	inputs: string;
+	parameters?: TextGenerationInputGenerateParameters;
+	stream?: boolean;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationInputGenerateParameters {
+	/**
+	 * Lora adapter id
+	 */
+	adapter_id?: string;
+	/**
+	 * Generate best_of sequences and return the one if the highest token logprobs.
+	 */
+	best_of?: number;
+	/**
+	 * Whether to return decoder input token logprobs and ids.
+	 */
+	decoder_input_details?: boolean;
+	/**
+	 * Whether to return generation details.
+	 */
+	details?: boolean;
+	/**
+	 * Activate logits sampling.
+	 */
+	do_sample?: boolean;
+	/**
+	 * The parameter for frequency penalty. 1.0 means no penalty
+	 * Penalize new tokens based on their existing frequency in the text so far,
+	 * decreasing the model's likelihood to repeat the same line verbatim.
+	 */
+	frequency_penalty?: number;
+	grammar?: TextGenerationInputGrammarType;
+	/**
+	 * Maximum number of tokens to generate.
+	 */
+	max_new_tokens?: number;
+	/**
+	 * The parameter for repetition penalty. 1.0 means no penalty.
+	 * See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.
+	 */
+	repetition_penalty?: number;
+	/**
+	 * Whether to prepend the prompt to the generated text
+	 */
+	return_full_text?: boolean;
+	/**
+	 * Random sampling seed.
+	 */
+	seed?: number;
+	/**
+	 * Stop generating tokens if a member of `stop` is generated.
+	 */
+	stop?: string[];
+	/**
+	 * The value used to module the logits distribution.
+	 */
+	temperature?: number;
+	/**
+	 * The number of highest probability vocabulary tokens to keep for top-k-filtering.
+	 */
+	top_k?: number;
+	/**
+	 * The number of highest probability vocabulary tokens to keep for top-n-filtering.
+	 */
+	top_n_tokens?: number;
+	/**
+	 * Top-p value for nucleus sampling.
+	 */
+	top_p?: number;
+	/**
+	 * Truncate inputs tokens to the given size.
+	 */
+	truncate?: number;
+	/**
+	 * Typical Decoding mass
+	 * See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666)
+	 * for more information.
+	 */
+	typical_p?: number;
+	/**
+	 * Watermarking with [A Watermark for Large Language
+	 * Models](https://arxiv.org/abs/2301.10226).
+	 */
+	watermark?: boolean;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationInputGrammarType {
+	type: Type;
+	/**
+	 * A string that represents a [JSON Schema](https://json-schema.org/).
+	 *
+	 * JSON Schema is a declarative language that allows to annotate JSON documents
+	 * with types and descriptions.
+	 */
+	value: unknown;
+	[property: string]: unknown;
+}
+
+export type Type = "json" | "regex";
+
+/**
+ * Text Generation Output.
+ *
+ * Auto-generated from TGI specs.
+ * For more details, check out
+ * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
+ */
+export interface TextGenerationOutput {
+	details?: TextGenerationOutputDetails;
+	generated_text: string;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationOutputDetails {
+	best_of_sequences?: TextGenerationOutputBestOfSequence[];
+	finish_reason: TextGenerationOutputFinishReason;
+	generated_tokens: number;
+	prefill: TextGenerationOutputPrefillToken[];
+	seed?: number;
+	tokens: TextGenerationOutputToken[];
+	top_tokens?: Array<TextGenerationOutputToken[]>;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationOutputBestOfSequence {
+	finish_reason: TextGenerationOutputFinishReason;
+	generated_text: string;
+	generated_tokens: number;
+	prefill: TextGenerationOutputPrefillToken[];
+	seed?: number;
+	tokens: TextGenerationOutputToken[];
+	top_tokens?: Array<TextGenerationOutputToken[]>;
+	[property: string]: unknown;
+}
+
+export type TextGenerationOutputFinishReason = "length" | "eos_token" | "stop_sequence";
+
+export interface TextGenerationOutputPrefillToken {
+	id: number;
+	logprob: number;
+	text: string;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationOutputToken {
+	id: number;
+	logprob: number;
+	special: boolean;
+	text: string;
+	[property: string]: unknown;
+}
+
+/**
+ * Text Generation Stream Output.
+ *
+ * Auto-generated from TGI specs.
+ * For more details, check out
+ * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
+ */
+export interface TextGenerationStreamOutput {
+	details?: TextGenerationStreamOutputStreamDetails;
+	generated_text?: string;
+	index: number;
+	token: TextGenerationStreamOutputToken;
+	top_tokens?: TextGenerationStreamOutputToken[];
+	[property: string]: unknown;
+}
+
+export interface TextGenerationStreamOutputStreamDetails {
+	finish_reason: TextGenerationOutputFinishReason;
+	generated_tokens: number;
+	input_length: number;
+	seed?: number;
+	[property: string]: unknown;
+}
+
+export interface TextGenerationStreamOutputToken {
+	id: number;
+	logprob: number;
+	special: boolean;
+	text: string;
+	[property: string]: unknown;
+}

package/src/tasks/text-generation/spec/input.json

@@ -0,0 +1,219 @@
+{
+	"$id": "/inference/schemas/text-generation/input.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Text Generation Input.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
+	"title": "TextGenerationInput",
+	"type": "object",
+	"required": ["inputs"],
+	"properties": {
+		"inputs": {
+			"type": "string",
+			"example": "My name is Olivier and I"
+		},
+		"parameters": {
+			"$ref": "#/$defs/TextGenerationInputGenerateParameters"
+		},
+		"stream": {
+			"type": "boolean",
+			"default": "false"
+		}
+	},
+	"$defs": {
+		"TextGenerationInputGenerateParameters": {
+			"type": "object",
+			"properties": {
+				"adapter_id": {
+					"type": "string",
+					"description": "Lora adapter id",
+					"default": "null",
+					"example": "null",
+					"nullable": true
+				},
+				"best_of": {
+					"type": "integer",
+					"description": "Generate best_of sequences and return the one if the highest token logprobs.",
+					"default": "null",
+					"example": 1,
+					"nullable": true,
+					"minimum": 0,
+					"exclusiveMinimum": 0
+				},
+				"decoder_input_details": {
+					"type": "boolean",
+					"description": "Whether to return decoder input token logprobs and ids.",
+					"default": "false"
+				},
+				"details": {
+					"type": "boolean",
+					"description": "Whether to return generation details.",
+					"default": "true"
+				},
+				"do_sample": {
+					"type": "boolean",
+					"description": "Activate logits sampling.",
+					"default": "false",
+					"example": true
+				},
+				"frequency_penalty": {
+					"type": "number",
+					"format": "float",
+					"description": "The parameter for frequency penalty. 1.0 means no penalty\nPenalize new tokens based on their existing frequency in the text so far,\ndecreasing the model's likelihood to repeat the same line verbatim.",
+					"default": "null",
+					"example": 0.1,
+					"nullable": true,
+					"exclusiveMinimum": -2
+				},
+				"grammar": {
+					"allOf": [
+						{
+							"$ref": "#/$defs/TextGenerationInputGrammarType"
+						}
+					],
+					"default": "null",
+					"nullable": true
+				},
+				"max_new_tokens": {
+					"type": "integer",
+					"format": "int32",
+					"description": "Maximum number of tokens to generate.",
+					"default": "100",
+					"example": "20",
+					"nullable": true,
+					"minimum": 0
+				},
+				"repetition_penalty": {
+					"type": "number",
+					"format": "float",
+					"description": "The parameter for repetition penalty. 1.0 means no penalty.\nSee [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.",
+					"default": "null",
+					"example": 1.03,
+					"nullable": true,
+					"exclusiveMinimum": 0
+				},
+				"return_full_text": {
+					"type": "boolean",
+					"description": "Whether to prepend the prompt to the generated text",
+					"default": "null",
+					"example": false,
+					"nullable": true
+				},
+				"seed": {
+					"type": "integer",
+					"format": "int64",
+					"description": "Random sampling seed.",
+					"default": "null",
+					"example": "null",
+					"nullable": true,
+					"minimum": 0,
+					"exclusiveMinimum": 0
+				},
+				"stop": {
+					"type": "array",
+					"items": {
+						"type": "string"
+					},
+					"description": "Stop generating tokens if a member of `stop` is generated.",
+					"example": ["photographer"],
+					"maxItems": 4
+				},
+				"temperature": {
+					"type": "number",
+					"format": "float",
+					"description": "The value used to module the logits distribution.",
+					"default": "null",
+					"example": 0.5,
+					"nullable": true,
+					"exclusiveMinimum": 0
+				},
+				"top_k": {
+					"type": "integer",
+					"format": "int32",
+					"description": "The number of highest probability vocabulary tokens to keep for top-k-filtering.",
+					"default": "null",
+					"example": 10,
+					"nullable": true,
+					"exclusiveMinimum": 0
+				},
+				"top_n_tokens": {
+					"type": "integer",
+					"format": "int32",
+					"description": "The number of highest probability vocabulary tokens to keep for top-n-filtering.",
+					"default": "null",
+					"example": 5,
+					"nullable": true,
+					"minimum": 0,
+					"exclusiveMinimum": 0
+				},
+				"top_p": {
+					"type": "number",
+					"format": "float",
+					"description": "Top-p value for nucleus sampling.",
+					"default": "null",
+					"example": 0.95,
+					"nullable": true,
+					"maximum": 1,
+					"exclusiveMinimum": 0
+				},
+				"truncate": {
+					"type": "integer",
+					"description": "Truncate inputs tokens to the given size.",
+					"default": "null",
+					"example": "null",
+					"nullable": true,
+					"minimum": 0
+				},
+				"typical_p": {
+					"type": "number",
+					"format": "float",
+					"description": "Typical Decoding mass\nSee [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information.",
+					"default": "null",
+					"example": 0.95,
+					"nullable": true,
+					"maximum": 1,
+					"exclusiveMinimum": 0
+				},
+				"watermark": {
+					"type": "boolean",
+					"description": "Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226).",
+					"default": "false",
+					"example": true
+				}
+			},
+			"title": "TextGenerationInputGenerateParameters"
+		},
+		"TextGenerationInputGrammarType": {
+			"oneOf": [
+				{
+					"type": "object",
+					"required": ["type", "value"],
+					"properties": {
+						"type": {
+							"type": "string",
+							"enum": ["json"]
+						},
+						"value": {
+							"description": "A string that represents a [JSON Schema](https://json-schema.org/).\n\nJSON Schema is a declarative language that allows to annotate JSON documents\nwith types and descriptions."
+						}
+					}
+				},
+				{
+					"type": "object",
+					"required": ["type", "value"],
+					"properties": {
+						"type": {
+							"type": "string",
+							"enum": ["regex"]
+						},
+						"value": {
+							"type": "string"
+						}
+					}
+				}
+			],
+			"discriminator": {
+				"propertyName": "type"
+			},
+			"title": "TextGenerationInputGrammarType"
+		}
+	}
+}

package/src/tasks/text-generation/spec/output.json

@@ -0,0 +1,179 @@
+{
+	"$id": "/inference/schemas/text-generation/output.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Text Generation Output.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
+	"title": "TextGenerationOutput",
+	"type": "object",
+	"required": ["generated_text"],
+	"properties": {
+		"details": {
+			"allOf": [
+				{
+					"$ref": "#/$defs/TextGenerationOutputDetails"
+				}
+			],
+			"nullable": true
+		},
+		"generated_text": {
+			"type": "string",
+			"example": "test"
+		}
+	},
+	"$defs": {
+		"TextGenerationOutputDetails": {
+			"type": "object",
+			"required": ["finish_reason", "generated_tokens", "prefill", "tokens"],
+			"properties": {
+				"best_of_sequences": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/TextGenerationOutputBestOfSequence"
+					},
+					"nullable": true
+				},
+				"finish_reason": {
+					"$ref": "#/$defs/TextGenerationOutputFinishReason"
+				},
+				"generated_tokens": {
+					"type": "integer",
+					"format": "int32",
+					"example": 1,
+					"minimum": 0
+				},
+				"prefill": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/TextGenerationOutputPrefillToken"
+					}
+				},
+				"seed": {
+					"type": "integer",
+					"format": "int64",
+					"example": 42,
+					"nullable": true,
+					"minimum": 0
+				},
+				"tokens": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/TextGenerationOutputToken"
+					}
+				},
+				"top_tokens": {
+					"type": "array",
+					"items": {
+						"type": "array",
+						"items": {
+							"$ref": "#/$defs/TextGenerationOutputToken"
+						}
+					}
+				}
+			},
+			"title": "TextGenerationOutputDetails"
+		},
+		"TextGenerationOutputBestOfSequence": {
+			"type": "object",
+			"required": ["generated_text", "finish_reason", "generated_tokens", "prefill", "tokens"],
+			"properties": {
+				"finish_reason": {
+					"$ref": "#/$defs/TextGenerationOutputFinishReason"
+				},
+				"generated_text": {
+					"type": "string",
+					"example": "test"
+				},
+				"generated_tokens": {
+					"type": "integer",
+					"format": "int32",
+					"example": 1,
+					"minimum": 0
+				},
+				"prefill": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/TextGenerationOutputPrefillToken"
+					}
+				},
+				"seed": {
+					"type": "integer",
+					"format": "int64",
+					"example": 42,
+					"nullable": true,
+					"minimum": 0
+				},
+				"tokens": {
+					"type": "array",
+					"items": {
+						"$ref": "#/$defs/TextGenerationOutputToken"
+					}
+				},
+				"top_tokens": {
+					"type": "array",
+					"items": {
+						"type": "array",
+						"items": {
+							"$ref": "#/$defs/TextGenerationOutputToken"
+						}
+					}
+				}
+			},
+			"title": "TextGenerationOutputBestOfSequence"
+		},
+		"TextGenerationOutputFinishReason": {
+			"type": "string",
+			"enum": ["length", "eos_token", "stop_sequence"],
+			"example": "Length",
+			"title": "TextGenerationOutputFinishReason"
+		},
+		"TextGenerationOutputPrefillToken": {
+			"type": "object",
+			"required": ["id", "text", "logprob"],
+			"properties": {
+				"id": {
+					"type": "integer",
+					"format": "int32",
+					"example": 0,
+					"minimum": 0
+				},
+				"logprob": {
+					"type": "number",
+					"format": "float",
+					"example": -0.34,
+					"nullable": true
+				},
+				"text": {
+					"type": "string",
+					"example": "test"
+				}
+			},
+			"title": "TextGenerationOutputPrefillToken"
+		},
+		"TextGenerationOutputToken": {
+			"type": "object",
+			"required": ["id", "text", "logprob", "special"],
+			"properties": {
+				"id": {
+					"type": "integer",
+					"format": "int32",
+					"example": 0,
+					"minimum": 0
+				},
+				"logprob": {
+					"type": "number",
+					"format": "float",
+					"example": -0.34,
+					"nullable": true
+				},
+				"special": {
+					"type": "boolean",
+					"example": "false"
+				},
+				"text": {
+					"type": "string",
+					"example": "test"
+				}
+			},
+			"title": "TextGenerationOutputToken"
+		}
+	}
+}

package/src/tasks/text-generation/spec/stream_output.json

@@ -0,0 +1,103 @@
+{
+	"$id": "/inference/schemas/text-generation/stream_output.json",
+	"$schema": "http://json-schema.org/draft-06/schema#",
+	"description": "Text Generation Stream Output.\n\nAuto-generated from TGI specs.\nFor more details, check out https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.",
+	"title": "TextGenerationStreamOutput",
+	"type": "object",
+	"required": ["index", "token"],
+	"properties": {
+		"details": {
+			"allOf": [
+				{
+					"$ref": "#/$defs/TextGenerationStreamOutputStreamDetails"
+				}
+			],
+			"default": "null",
+			"nullable": true
+		},
+		"generated_text": {
+			"type": "string",
+			"default": "null",
+			"example": "test",
+			"nullable": true
+		},
+		"index": {
+			"type": "integer",
+			"format": "int32",
+			"minimum": 0
+		},
+		"token": {
+			"$ref": "#/$defs/TextGenerationStreamOutputToken"
+		},
+		"top_tokens": {
+			"type": "array",
+			"items": {
+				"$ref": "#/$defs/TextGenerationStreamOutputToken"
+			}
+		}
+	},
+	"$defs": {
+		"TextGenerationStreamOutputStreamDetails": {
+			"type": "object",
+			"required": ["finish_reason", "generated_tokens", "input_length"],
+			"properties": {
+				"finish_reason": {
+					"$ref": "#/$defs/TextGenerationStreamOutputFinishReason"
+				},
+				"generated_tokens": {
+					"type": "integer",
+					"format": "int32",
+					"example": 1,
+					"minimum": 0
+				},
+				"input_length": {
+					"type": "integer",
+					"format": "int32",
+					"example": 1,
+					"minimum": 0
+				},
+				"seed": {
+					"type": "integer",
+					"format": "int64",
+					"example": 42,
+					"nullable": true,
+					"minimum": 0
+				}
+			},
+			"title": "TextGenerationStreamOutputStreamDetails"
+		},
+		"TextGenerationStreamOutputFinishReason": {
+			"type": "string",
+			"enum": ["length", "eos_token", "stop_sequence"],
+			"example": "Length",
+			"title": "TextGenerationStreamOutputFinishReason"
+		},
+		"TextGenerationStreamOutputToken": {
+			"type": "object",
+			"required": ["id", "text", "logprob", "special"],
+			"properties": {
+				"id": {
+					"type": "integer",
+					"format": "int32",
+					"example": 0,
+					"minimum": 0
+				},
+				"logprob": {
+					"type": "number",
+					"format": "float",
+					"example": -0.34,
+					"nullable": true
+				},
+				"special": {
+					"type": "boolean",
+					"example": "false"
+				},
+				"text": {
+					"type": "string",
+					"example": "test"
+				}
+			},
+			"title": "TextGenerationStreamOutputToken"
+		}
+	}
+}