@huggingface/tasks 0.9.1 → 0.10.1

package/src/local-apps.ts

@@ -0,0 +1,119 @@
+import type { ModelData } from "./model-data";
+import type { PipelineType } from "./pipelines";
+
+/**
+ * Elements configurable by a local app.
+ */
+export type LocalApp = {
+	/**
+	 * Name that appears in buttons
+	 */
+	prettyLabel: string;
+	/**
+	 * Link to get more info about a local app (website etc)
+	 */
+	docsUrl: string;
+	/**
+	 * main category of app
+	 */
+	mainTask: PipelineType;
+	/**
+	 * Whether to display a pill "macOS-only"
+	 */
+	macOSOnly?: boolean;
+
+	comingSoon?: boolean;
+	/**
+	 * IMPORTANT: function to figure out whether to display the button on a model page's main "Use this model" dropdown.
+	 */
+	displayOnModelPage: (model: ModelData) => boolean;
+} & (
+	| {
+			/**
+			 * If the app supports deeplink, URL to open.
+			 */
+			deeplink: (model: ModelData) => URL;
+	  }
+	| {
+			/**
+			 * And if not (mostly llama.cpp), snippet to copy/paste in your terminal
+			 */
+			snippet: (model: ModelData) => string;
+	  }
+);
+
+function isGgufModel(model: ModelData) {
+	return model.tags.includes("gguf");
+}
+
+const snippetLlamacpp = (model: ModelData): string => {
+	return `./main \
+	--hf-repo ${model.id} \
+	-m file.gguf \
+	-p "I believe the meaning of life is " -n 128`;
+};
+
+/**
+ * Add your new local app here.
+ *
+ * This is open to new suggestions and awesome upcoming apps.
+ *
+ * /!\ IMPORTANT
+ *
+ * If possible, you need to support deeplinks and be as cross-platform as possible.
+ *
+ * Ping the HF team if we can help with anything!
+ */
+export const LOCAL_APPS = {
+	"llama.cpp": {
+		prettyLabel: "llama.cpp",
+		docsUrl: "https://github.com/ggerganov/llama.cpp",
+		mainTask: "text-generation",
+		displayOnModelPage: isGgufModel,
+		snippet: snippetLlamacpp,
+	},
+	lmstudio: {
+		prettyLabel: "LM Studio",
+		docsUrl: "https://lmstudio.ai",
+		mainTask: "text-generation",
+		displayOnModelPage: isGgufModel,
+		deeplink: (model) => new URL(`lmstudio://open_from_hf?model=${model.id}`),
+	},
+	jan: {
+		prettyLabel: "Jan",
+		docsUrl: "https://jan.ai",
+		mainTask: "text-generation",
+		displayOnModelPage: isGgufModel,
+		deeplink: (model) => new URL(`jan://open_from_hf?model=${model.id}`),
+	},
+	faraday: {
+		prettyLabel: "Faraday",
+		docsUrl: "https://faraday.dev",
+		mainTask: "text-generation",
+		macOSOnly: true,
+		displayOnModelPage: isGgufModel,
+		deeplink: (model) => new URL(`faraday://open_from_hf?model=${model.id}`),
+	},
+	drawthings: {
+		prettyLabel: "Draw Things",
+		docsUrl: "https://drawthings.ai",
+		mainTask: "text-to-image",
+		macOSOnly: true,
+		/**
+		 * random function, will need to refine the actual conditions:
+		 */
+		displayOnModelPage: (model) => model.tags.includes("textual_inversion"),
+		deeplink: (model) => new URL(`drawthings://open_from_hf?model=${model.id}`),
+	},
+	diffusionbee: {
+		prettyLabel: "DiffusionBee",
+		docsUrl: "https://diffusionbee.com",
+		mainTask: "text-to-image",
+		macOSOnly: true,
+		comingSoon: true,
+		displayOnModelPage: (model) => model.library_name === "diffusers" && model.pipeline_tag === "text-to-image",
+		deeplink: (model) => new URL(`diffusionbee://open_from_hf?model=${model.id}`),
+	},
+} satisfies Record<string, LocalApp>;
+
+export type LocalAppKey = keyof typeof LOCAL_APPS;

package/src/model-data.ts

@@ -25,10 +25,6 @@ export interface ModelData {
 	 * id of model (e.g. 'user/repo_name')
 	 */
 	id: string;
-	/**
-	 * Kept for backward compatibility
-	 */
-	modelId?: string;
 	/**
 	 * Whether or not to enable inference widget for this model
 	 */
@@ -84,7 +80,7 @@ export interface ModelData {
 	/**
 	 * all the model tags
 	 */
-	tags?: string[];
+	tags: string[];
 	/**
 	 * transformers-specific info to display in the code sample.
 	 */

package/src/model-libraries-snippets.ts

@@ -33,7 +33,7 @@ predictions = predictor.predict_json(predictor_input)`,
 ];
 
 export const allennlp = (model: ModelData): string[] => {
-	if (model.tags?.includes("question-answering")) {
+	if (model.tags.includes("question-answering")) {
 		return allennlpQuestionAnswering(model);
 	}
 	return allennlpUnknown(model);
@@ -85,11 +85,11 @@ pipeline.load_textual_inversion("${model.id}")`,
 ];
 
 export const diffusers = (model: ModelData): string[] => {
-	if (model.tags?.includes("controlnet")) {
+	if (model.tags.includes("controlnet")) {
 		return diffusers_controlnet(model);
-	} else if (model.tags?.includes("lora")) {
+	} else if (model.tags.includes("lora")) {
 		return diffusers_lora(model);
-	} else if (model.tags?.includes("textual_inversion")) {
+	} else if (model.tags.includes("textual_inversion")) {
 		return diffusers_textual_inversion(model);
 	} else {
 		return diffusers_default(model);
@@ -118,9 +118,9 @@ text, *_ = model(speech)[0]`,
 const espnetUnknown = () => [`unknown model type (must be text-to-speech or automatic-speech-recognition)`];
 
 export const espnet = (model: ModelData): string[] => {
-	if (model.tags?.includes("text-to-speech")) {
+	if (model.tags.includes("text-to-speech")) {
 		return espnetTTS(model);
-	} else if (model.tags?.includes("automatic-speech-recognition")) {
+	} else if (model.tags.includes("automatic-speech-recognition")) {
 		return espnetASR(model);
 	}
 	return espnetUnknown();
@@ -154,7 +154,10 @@ model = from_pretrained_keras("${model.id}")
 ];
 
 export const keras_nlp = (model: ModelData): string[] => [
-	`import keras_nlp
+	`# Available backend options are: "jax", "tensorflow", "torch".
+os.environ["KERAS_BACKEND"] = "tensorflow"
+
+import keras_nlp
 
 tokenizer = keras_nlp.models.Tokenizer.from_preset("hf://${model.id}")
 backbone = keras_nlp.models.Backbone.from_preset("hf://${model.id}")
@@ -225,7 +228,7 @@ inference.crop("file.wav", excerpt)`,
 ];
 
 export const pyannote_audio = (model: ModelData): string[] => {
-	if (model.tags?.includes("pyannote-audio-pipeline")) {
+	if (model.tags.includes("pyannote-audio-pipeline")) {
 		return pyannote_audio_pipeline(model);
 	}
 	return pyannote_audio_model(model);
@@ -255,9 +258,9 @@ model = TFAutoModel.from_pretrained("${model.id}")
 ];
 
 export const tensorflowtts = (model: ModelData): string[] => {
-	if (model.tags?.includes("text-to-mel")) {
+	if (model.tags.includes("text-to-mel")) {
 		return tensorflowttsTextToMel(model);
-	} else if (model.tags?.includes("mel-to-wav")) {
+	} else if (model.tags.includes("mel-to-wav")) {
 		return tensorflowttsMelToWav(model);
 	}
 	return tensorflowttsUnknown(model);
@@ -306,7 +309,7 @@ model = joblib.load(
 };
 
 export const sklearn = (model: ModelData): string[] => {
-	if (model.tags?.includes("skops")) {
+	if (model.tags.includes("skops")) {
 		const skopsmodelFile = model.config?.sklearn?.model?.file;
 		const skopssaveFormat = model.config?.sklearn?.model_format;
 		if (!skopsmodelFile) {
@@ -410,7 +413,7 @@ export const transformers = (model: ModelData): string[] => {
 	if (!info) {
 		return [`# ⚠️ Type of model unknown`];
 	}
-	const remote_code_snippet = model.tags?.includes(TAG_CUSTOM_CODE) ? ", trust_remote_code=True" : "";
+	const remote_code_snippet = model.tags.includes(TAG_CUSTOM_CODE) ? ", trust_remote_code=True" : "";
 
 	let autoSnippet: string;
 	if (info.processor) {
@@ -493,8 +496,8 @@ export const peft = (model: ModelData): string[] => {
 from transformers import AutoModelFor${pefttask}
 
 config = PeftConfig.from_pretrained("${model.id}")
-model = AutoModelFor${pefttask}.from_pretrained("${peftBaseModel}")
-model = PeftModel.from_pretrained(model, "${model.id}")`,
+base_model = AutoModelFor${pefttask}.from_pretrained("${peftBaseModel}")
+model = PeftModel.from_pretrained(base_model, "${model.id}")`,
 	];
 };
 
@@ -561,7 +564,7 @@ model = create_model(${model.id})`,
 export const nemo = (model: ModelData): string[] => {
 	let command: string[] | undefined = undefined;
 	// Resolve the tag to a nemo domain/sub-domain
-	if (model.tags?.includes("automatic-speech-recognition")) {
+	if (model.tags.includes("automatic-speech-recognition")) {
 		command = nemoDomainResolver("ASR", model);
 	}
 
@@ -602,11 +605,11 @@ wav = model.generate(descriptions)  # generates 3 samples.`,
 ];
 
 export const audiocraft = (model: ModelData): string[] => {
-	if (model.tags?.includes("musicgen")) {
+	if (model.tags.includes("musicgen")) {
 		return musicgen(model);
-	} else if (model.tags?.includes("audiogen")) {
+	} else if (model.tags.includes("audiogen")) {
 		return audiogen(model);
-	} else if (model.tags?.includes("magnet")) {
+	} else if (model.tags.includes("magnet")) {
 		return magnet(model);
 	} else {
 		return [`# Type of model unknown.`];

package/src/model-libraries.ts

@@ -380,6 +380,15 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		repoUrl: "https://github.com/TensorSpeech/TensorFlowTTS",
 		snippets: snippets.tensorflowtts,
 	},
+	timesfm: {
+		prettyLabel: "TimesFM",
+		repoName: "timesfm",
+		repoUrl: "https://github.com/google-research/timesfm",
+		filter: false,
+		countDownloads: {
+			term: { path: "checkpoints/checkpoint_1100000/state/checkpoint" },
+		},
+	},
 	timm: {
 		prettyLabel: "timm",
 		repoName: "pytorch-image-models",

package/src/tasks/chat-completion/inference.ts

@@ -5,154 +5,273 @@
  */
 
 /**
- * Inputs for ChatCompletion inference
+ * Chat Completion 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 ChatCompletionInput {
 	/**
 	 * Number between -2.0 and 2.0. Positive values 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 in the text so far,
+	 * decreasing the model's likelihood to repeat the same line verbatim.
 	 */
 	frequency_penalty?: number;
+	/**
+	 * UNUSED
+	 * Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON
+	 * object that maps tokens
+	 * (specified by their token ID in the tokenizer) to an associated bias value from -100 to
+	 * 100. Mathematically,
+	 * the bias is added to the logits generated by the model prior to sampling. The exact
+	 * effect will vary per model,
+	 * but values between -1 and 1 should decrease or increase likelihood of selection; values
+	 * like -100 or 100 should
+	 * result in a ban or exclusive selection of the relevant token.
+	 */
+	logit_bias?: number[];
+	/**
+	 * Whether to return log probabilities of the output tokens or not. If true, returns the log
+	 * probabilities of each
+	 * output token returned in the content of message.
+	 */
+	logprobs?: boolean;
 	/**
 	 * The maximum number of tokens that can be generated in the chat completion.
 	 */
 	max_tokens?: number;
+	/**
+	 * A list of messages comprising the conversation so far.
+	 */
 	messages: ChatCompletionInputMessage[];
 	/**
-	 * The random sampling seed.
+	 * [UNUSED] ID of the model to use. See the model endpoint compatibility table for details
+	 * on which models work with the Chat API.
 	 */
-	seed?: number;
+	model: string;
+	/**
+	 * UNUSED
+	 * How many chat completion choices to generate for each input message. Note that you will
+	 * be charged based on the
+	 * number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
+	 */
+	n?: number;
 	/**
-	 * Stop generating tokens if a stop token is generated.
+	 * Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they
+	 * appear in the text so far,
+	 * increasing the model's likelihood to talk about new topics
 	 */
-	stop?: ChatCompletionInputStopReason;
+	presence_penalty?: number;
+	seed?: number;
 	/**
-	 * If set, partial message deltas will be sent.
+	 * Up to 4 sequences where the API will stop generating further tokens.
 	 */
+	stop?: string[];
 	stream?: boolean;
 	/**
-	 * The value used to modulate the logits distribution.
+	 * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the
+	 * output more random, while
+	 * lower values like 0.2 will make it more focused and deterministic.
+	 *
+	 * We generally recommend altering this or `top_p` but not both.
 	 */
 	temperature?: number;
+	tool_choice?: ChatCompletionInputToolType;
+	/**
+	 * A prompt to be appended before the tools
+	 */
+	tool_prompt?: string;
 	/**
-	 * If set to < 1, only the smallest set of most probable tokens with probabilities that add
-	 * up to `top_p` or higher are kept for generation.
+	 * A list of tools the model may call. Currently, only functions are supported as a tool.
+	 * Use this to provide a list of
+	 * functions the model may generate JSON inputs for.
+	 */
+	tools?: ChatCompletionInputTool[];
+	/**
+	 * An integer between 0 and 5 specifying the number of most likely tokens to return at each
+	 * token position, each with
+	 * an associated log probability. logprobs must be set to true if this parameter is used.
+	 */
+	top_logprobs?: number;
+	/**
+	 * An alternative to sampling with temperature, called nucleus sampling, where the model
+	 * considers the results of the
+	 * tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10%
+	 * probability mass are considered.
 	 */
 	top_p?: number;
 	[property: string]: unknown;
 }
 
 export interface ChatCompletionInputMessage {
-	/**
-	 * The content of the message.
-	 */
-	content: string;
-	role: ChatCompletionMessageRole;
+	content?: string;
+	name?: string;
+	role: string;
+	tool_calls?: ChatCompletionInputToolCall[];
 	[property: string]: unknown;
 }
 
-/**
- * The role of the message author.
- */
-export type ChatCompletionMessageRole = "assistant" | "system" | "user";
+export interface ChatCompletionInputToolCall {
+	function: ChatCompletionInputFunctionDefinition;
+	id: number;
+	type: string;
+	[property: string]: unknown;
+}
 
-/**
- * Stop generating tokens if a stop token is generated.
- */
-export type ChatCompletionInputStopReason = string[] | string;
+export interface ChatCompletionInputFunctionDefinition {
+	arguments: unknown;
+	description?: string;
+	name: string;
+	[property: string]: unknown;
+}
+
+export type ChatCompletionInputToolType = "OneOf" | ChatCompletionInputToolTypeObject;
+
+export interface ChatCompletionInputToolTypeObject {
+	FunctionName: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionInputTool {
+	function: ChatCompletionInputFunctionDefinition;
+	type: string;
+	[property: string]: unknown;
+}
 
 /**
- * Outputs for Chat Completion inference
+ * Chat Completion 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 ChatCompletionOutput {
-	/**
-	 * A list of chat completion choices.
-	 */
-	choices: ChatCompletionOutputChoice[];
-	/**
-	 * The Unix timestamp (in seconds) of when the chat completion was created.
-	 */
+	choices: ChatCompletionOutputComplete[];
 	created: number;
+	id: string;
+	model: string;
+	object: string;
+	system_fingerprint: string;
+	usage: ChatCompletionOutputUsage;
 	[property: string]: unknown;
 }
 
-export interface ChatCompletionOutputChoice {
-	/**
-	 * The reason why the generation was stopped.
-	 */
-	finish_reason: ChatCompletionFinishReason;
-	/**
-	 * The index of the choice in the list of choices.
-	 */
+export interface ChatCompletionOutputComplete {
+	finish_reason: string;
 	index: number;
-	message: ChatCompletionOutputChoiceMessage;
+	logprobs?: ChatCompletionOutputLogprobs;
+	message: ChatCompletionOutputMessage;
 	[property: string]: unknown;
 }
 
-/**
- * The reason why the generation was stopped.
- *
- * The generated sequence reached the maximum allowed length
- *
- * The model generated an end-of-sentence (EOS) token
- *
- * One of the sequence in stop_sequences was generated
- */
-export type ChatCompletionFinishReason = "length" | "eos_token" | "stop_sequence";
+export interface ChatCompletionOutputLogprobs {
+	content: ChatCompletionOutputLogprob[];
+	[property: string]: unknown;
+}
 
-export interface ChatCompletionOutputChoiceMessage {
-	/**
-	 * The content of the chat completion message.
-	 */
-	content: string;
-	role: ChatCompletionMessageRole;
+export interface ChatCompletionOutputLogprob {
+	logprob: number;
+	token: string;
+	top_logprobs: ChatCompletionOutputTopLogprob[];
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionOutputTopLogprob {
+	logprob: number;
+	token: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionOutputMessage {
+	content?: string;
+	name?: string;
+	role: string;
+	tool_calls?: ChatCompletionOutputToolCall[];
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionOutputToolCall {
+	function: ChatCompletionOutputFunctionDefinition;
+	id: number;
+	type: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionOutputFunctionDefinition {
+	arguments: unknown;
+	description?: string;
+	name: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionOutputUsage {
+	completion_tokens: number;
+	prompt_tokens: number;
+	total_tokens: number;
 	[property: string]: unknown;
 }
 
 /**
- * Chat Completion Stream Output
+ * Chat Completion 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 ChatCompletionStreamOutput {
-	/**
-	 * A list of chat completion choices.
-	 */
 	choices: ChatCompletionStreamOutputChoice[];
-	/**
-	 * The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has
-	 * the same timestamp.
-	 */
 	created: number;
+	id: string;
+	model: string;
+	object: string;
+	system_fingerprint: string;
 	[property: string]: unknown;
 }
 
 export interface ChatCompletionStreamOutputChoice {
-	/**
-	 * A chat completion delta generated by streamed model responses.
-	 */
 	delta: ChatCompletionStreamOutputDelta;
-	/**
-	 * The reason why the generation was stopped.
-	 */
-	finish_reason?: ChatCompletionFinishReason;
-	/**
-	 * The index of the choice in the list of choices.
-	 */
+	finish_reason?: string;
 	index: number;
+	logprobs?: ChatCompletionStreamOutputLogprobs;
 	[property: string]: unknown;
 }
 
-/**
- * A chat completion delta generated by streamed model responses.
- */
 export interface ChatCompletionStreamOutputDelta {
-	/**
-	 * The contents of the chunk message.
-	 */
 	content?: string;
-	/**
-	 * The role of the author of this message.
-	 */
-	role?: string;
+	role: string;
+	tool_calls?: ChatCompletionStreamOutputDeltaToolCall;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionStreamOutputDeltaToolCall {
+	function: ChatCompletionStreamOutputFunction;
+	id: string;
+	index: number;
+	type: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionStreamOutputFunction {
+	arguments: string;
+	name?: string;
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionStreamOutputLogprobs {
+	content: ChatCompletionStreamOutputLogprob[];
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionStreamOutputLogprob {
+	logprob: number;
+	token: string;
+	top_logprobs: ChatCompletionStreamOutputTopLogprob[];
+	[property: string]: unknown;
+}
+
+export interface ChatCompletionStreamOutputTopLogprob {
+	logprob: number;
+	token: string;
 	[property: string]: unknown;
 }