@huggingface/tasks 0.11.11 → 0.11.13

package/src/model-libraries-snippets.ts

@@ -170,6 +170,87 @@ export const diffusers = (model: ModelData): string[] => {
 	}
 };
 
+export const diffusionkit = (model: ModelData): string[] => {
+	const sd3Snippet = `# Pipeline for Stable Diffusion 3
+from diffusionkit.mlx import DiffusionPipeline
+
+pipeline = DiffusionPipeline(
+	shift=3.0,
+	use_t5=False,
+	model_version=${model.id},
+	low_memory_mode=True,
+	a16=True,
+	w16=True,
+)`;
+
+	const fluxSnippet = `# Pipeline for Flux
+from diffusionkit.mlx import FluxPipeline
+
+pipeline = FluxPipeline(
+  shift=1.0,
+  model_version=${model.id},
+  low_memory_mode=True,
+  a16=True,
+  w16=True,
+)`;
+
+	const generateSnippet = `# Image Generation
+HEIGHT = 512
+WIDTH = 512
+NUM_STEPS = ${model.tags.includes("flux") ? 4 : 50}
+CFG_WEIGHT = ${model.tags.includes("flux") ? 0 : 5}
+
+image, _ = pipeline.generate_image(
+  "a photo of a cat",
+  cfg_weight=CFG_WEIGHT,
+  num_steps=NUM_STEPS,
+  latent_size=(HEIGHT // 8, WIDTH // 8),
+)`;
+
+	const pipelineSnippet = model.tags.includes("flux") ? fluxSnippet : sd3Snippet;
+
+	return [pipelineSnippet, generateSnippet];
+};
+
+export const cartesia_pytorch = (model: ModelData): string[] => [
+	`# pip install --no-binary :all: cartesia-pytorch
+from cartesia_pytorch import ReneLMHeadModel
+from transformers import AutoTokenizer
+
+model = ReneLMHeadModel.from_pretrained("${model.id}")
+tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-1B-hf")
+
+in_message = ["Rene Descartes was"]
+inputs = tokenizer(in_message, return_tensors="pt")
+
+outputs = model.generate(inputs.input_ids, max_length=50, top_k=100, top_p=0.99)
+out_message = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+
+print(out_message)
+)`,
+];
+
+export const cartesia_mlx = (model: ModelData): string[] => [
+	`import mlx.core as mx
+import cartesia_mlx as cmx
+
+model = cmx.from_pretrained("${model.id}")
+model.set_dtype(mx.float32)   
+
+prompt = "Rene Descartes was"
+
+for text in model.generate(
+    prompt,
+    max_tokens=500,
+    eval_every_n=5,
+    verbose=True,
+    top_p=0.99,
+    temperature=0.85,
+):
+    print(text, end="", flush=True)
+`,
+];
+
 export const edsnlp = (model: ModelData): string[] => {
 	const packageName = nameWithoutNamespace(model.id).replaceAll("-", "_");
 	return [
@@ -270,12 +351,12 @@ llm = Llama.from_pretrained(
 )
 
 llm.create_chat_completion(
-		messages = [
-			{
-				"role": "user",
-				"content": "What is the capital of France?"
-			}
-		]
+	messages = [
+		{
+			"role": "user",
+			"content": "What is the capital of France?"
+		}
+	]
 )`,
 ];
 

package/src/model-libraries.ts

@@ -150,6 +150,13 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		filter: false,
 		countDownloads: `path:"adapter_config.json"`,
 	},
+	deepforest: {
+		prettyLabel: "DeepForest",
+		repoName: "deepforest",
+		docsUrl: "https://deepforest.readthedocs.io/en/latest/",
+		repoUrl: "https://github.com/weecology/DeepForest",
+		countDownloads: `path_extension:"pt" OR path_extension:"pl"`,
+	},
 	"depth-anything-v2": {
 		prettyLabel: "DepthAnythingV2",
 		repoName: "Depth Anything V2",
@@ -174,11 +181,29 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		filter: true,
 		/// diffusers has its own more complex "countDownloads" query
 	},
+	diffusionkit: {
+		prettyLabel: "DiffusionKit",
+		repoName: "DiffusionKit",
+		repoUrl: "https://github.com/argmaxinc/DiffusionKit",
+		snippets: snippets.diffusionkit,
+	},
 	doctr: {
 		prettyLabel: "docTR",
 		repoName: "doctr",
 		repoUrl: "https://github.com/mindee/doctr",
 	},
+	cartesia_pytorch: {
+		prettyLabel: "Cartesia Pytorch",
+		repoName: "Cartesia Pytorch",
+		repoUrl: "https://github.com/cartesia-ai/cartesia_pytorch",
+		snippets: snippets.cartesia_pytorch,
+	},
+	cartesia_mlx: {
+		prettyLabel: "Cartesia MLX",
+		repoName: "Cartesia MLX",
+		repoUrl: "https://github.com/cartesia-ai/cartesia_mlx",
+		snippets: snippets.cartesia_mlx,
+	},
 	edsnlp: {
 		prettyLabel: "EDS-NLP",
 		repoName: "edsnlp",
@@ -421,6 +446,13 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
 		snippets: snippets.pyannote_audio,
 		filter: true,
 	},
+	"py-feat": {
+		prettyLabel: "Py-Feat",
+		repoName: "Py-Feat",
+		repoUrl: "https://github.com/cosanlab/py-feat",
+		docsUrl: "https://py-feat.org/",
+		filter: false,
+	},
 	pythae: {
 		prettyLabel: "pythae",
 		repoName: "pythae",

package/src/pipelines.ts

@@ -656,6 +656,18 @@ export const PIPELINE_DATA = {
 		name: "Video-Text-to-Text",
 		modality: "multimodal",
 		color: "blue",
+		hideInDatasets: false,
+	},
+	"keypoint-detection": {
+		name: "Keypoint Detection",
+		subtasks: [
+			{
+				type: "pose-estimation",
+				name: "Pose Estimation",
+			},
+		],
+		modality: "cv",
+		color: "red",
 		hideInDatasets: true,
 	},
 	other: {

package/src/snippets/curl.ts

@@ -7,8 +7,7 @@ export const snippetBasic = (model: ModelDataMinimal, accessToken: string): stri
 	-X POST \\
 	-d '{"inputs": ${getModelInputSnippet(model, true)}}' \\
 	-H 'Content-Type: application/json' \\
-	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"
-`;
+	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"`;
 
 export const snippetTextGeneration = (model: ModelDataMinimal, accessToken: string): string => {
 	if (model.config?.tokenizer_config?.chat_template) {
@@ -33,15 +32,13 @@ export const snippetZeroShotClassification = (model: ModelDataMinimal, accessTok
 	-X POST \\
 	-d '{"inputs": ${getModelInputSnippet(model, true)}, "parameters": {"candidate_labels": ["refund", "legal", "faq"]}}' \\
 	-H 'Content-Type: application/json' \\
-	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"
-`;
+	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"`;
 
 export const snippetFile = (model: ModelDataMinimal, accessToken: string): string =>
 	`curl https://api-inference.huggingface.co/models/${model.id} \\
 	-X POST \\
 	--data-binary '@${getModelInputSnippet(model, true, true)}' \\
-	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"
-`;
+	-H "Authorization: Bearer ${accessToken || `{API_TOKEN}`}"`;
 
 export const curlSnippets: Partial<Record<PipelineType, (model: ModelDataMinimal, accessToken: string) => string>> = {
 	// Same order as in js/src/lib/interfaces/Types.ts

package/src/snippets/js.ts

@@ -36,8 +36,7 @@ for await (const chunk of inference.chatCompletionStream({
 	max_tokens: 500,
 })) {
 	process.stdout.write(chunk.choices[0]?.delta?.content || "");
-}
-`;
+}`;
 	} else {
 		return snippetBasic(model, accessToken);
 	}

package/src/snippets/python.ts

@@ -15,8 +15,7 @@ for message in client.chat_completion(
 	max_tokens=500,
 	stream=True,
 ):
-    print(message.choices[0].delta.content, end="")
-`;
+    print(message.choices[0].delta.content, end="")`;
 
 export const snippetZeroShotClassification = (model: ModelDataMinimal): string =>
 	`def query(payload):

package/src/tasks/audio-classification/inference.ts

@@ -8,9 +8,10 @@
  */
 export interface AudioClassificationInput {
 	/**
-	 * The input audio data
+	 * The input audio data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the audio data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */

package/src/tasks/audio-classification/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input audio data"
+			"description": "The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload.",
+			"type": "string"
 		},
 		"parameters": {
 			"description": "Additional inference parameters",

package/src/tasks/audio-classification/spec/output.json

@@ -5,6 +5,7 @@
 	"description": "Outputs for Audio Classification inference",
 	"type": "array",
 	"items": {
+		"type": "object",
 		"$ref": "/inference/schemas/common-definitions.json#/definitions/ClassificationOutput"
 	}
 }

package/src/tasks/automatic-speech-recognition/inference.ts

@@ -9,9 +9,10 @@
  */
 export interface AutomaticSpeechRecognitionInput {
 	/**
-	 * The input audio data
+	 * The input audio data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the audio data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */

package/src/tasks/automatic-speech-recognition/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input audio data"
+			"description": "The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload.",
+			"type": "string"
 		},
 		"parameters": {
 			"description": "Additional inference parameters",

package/src/tasks/common-definitions.json

@@ -7,17 +7,7 @@
 			"title": "ClassificationOutputTransform",
 			"type": "string",
 			"description": "The function to apply to the model outputs in order to retrieve the scores.",
-			"oneOf": [
-				{
-					"const": "sigmoid"
-				},
-				{
-					"const": "softmax"
-				},
-				{
-					"const": "none"
-				}
-			]
+			"enum": ["sigmoid", "softmax", "none"]
 		},
 		"ClassificationOutput": {
 			"title": "ClassificationOutput",
@@ -84,16 +74,9 @@
 					"description": "Whether to use sampling instead of greedy decoding when generating new tokens."
 				},
 				"early_stopping": {
+					"type": ["boolean", "string"],
 					"description": "Controls the stopping condition for beam-based methods.",
-					"oneOf": [
-						{
-							"type": "boolean"
-						},
-						{
-							"const": "never",
-							"type": "string"
-						}
-					]
+					"enum": ["never", true, false]
 				},
 				"num_beams": {
 					"type": "integer",

package/src/tasks/image-classification/inference.ts

@@ -8,9 +8,10 @@
  */
 export interface ImageClassificationInput {
 	/**
-	 * The input image data
+	 * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the image data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */

package/src/tasks/image-classification/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input image data"
+			"type": "string",
+			"description": "The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload."
 		},
 		"parameters": {
 			"description": "Additional inference parameters",

package/src/tasks/image-classification/spec/output.json

@@ -5,6 +5,7 @@
 	"title": "ImageClassificationOutput",
 	"type": "array",
 	"items": {
+		"type": "object",
 		"$ref": "/inference/schemas/common-definitions.json#/definitions/ClassificationOutput"
 	}
 }

package/src/tasks/image-segmentation/inference.ts

@@ -8,9 +8,10 @@
  */
 export interface ImageSegmentationInput {
 	/**
-	 * The input image data
+	 * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the image data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */
@@ -41,6 +42,9 @@ export interface ImageSegmentationParameters {
 	threshold?: number;
 	[property: string]: unknown;
 }
+/**
+ * Segmentation task to be performed, depending on model capabilities.
+ */
 export type ImageSegmentationSubtask = "instance" | "panoptic" | "semantic";
 export type ImageSegmentationOutput = ImageSegmentationOutputElement[];
 /**
@@ -50,15 +54,15 @@ export type ImageSegmentationOutput = ImageSegmentationOutputElement[];
  */
 export interface ImageSegmentationOutputElement {
 	/**
-	 * The label of the predicted segment
+	 * The label of the predicted segment.
 	 */
 	label: string;
 	/**
-	 * The corresponding mask as a black-and-white image
+	 * The corresponding mask as a black-and-white image (base64-encoded).
 	 */
-	mask: unknown;
+	mask: string;
 	/**
-	 * The score or confidence degreee the model has
+	 * The score or confidence degree the model has.
 	 */
 	score?: number;
 	[property: string]: unknown;

package/src/tasks/image-segmentation/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input image data"
+			"type": "string",
+			"description": "The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload."
 		},
 		"parameters": {
 			"description": "Additional inference parameters",
@@ -31,17 +32,7 @@
 					"title": "ImageSegmentationSubtask",
 					"type": "string",
 					"description": "Segmentation task to be performed, depending on model capabilities.",
-					"oneOf": [
-						{
-							"const": "instance"
-						},
-						{
-							"const": "panoptic"
-						},
-						{
-							"const": "semantic"
-						}
-					]
+					"enum": ["instance", "panoptic", "semantic"]
 				},
 				"threshold": {
 					"type": "number",

package/src/tasks/image-segmentation/spec/output.json

@@ -10,14 +10,15 @@
 		"properties": {
 			"label": {
 				"type": "string",
-				"description": "The label of the predicted segment"
+				"description": "The label of the predicted segment."
 			},
 			"mask": {
-				"description": "The corresponding mask as a black-and-white image"
+				"type": "string",
+				"description": "The corresponding mask as a black-and-white image (base64-encoded)."
 			},
 			"score": {
 				"type": "number",
-				"description": "The score or confidence degreee the model has"
+				"description": "The score or confidence degree the model has."
 			}
 		},
 		"required": ["label", "mask"]

package/src/tasks/image-to-image/inference.ts

@@ -9,9 +9,10 @@
  */
 export interface ImageToImageInput {
 	/**
-	 * The input image data
+	 * The input image data as a base64-encoded string. If no `parameters` are provided, you can
+	 * also provide the image data as a raw bytes payload.
 	 */
-	inputs: unknown;
+	inputs: string;
 	/**
 	 * Additional inference parameters
 	 */
@@ -40,14 +41,14 @@ export interface ImageToImageParameters {
 	 */
 	num_inference_steps?: number;
 	/**
-	 * The size in pixel of the output image
+	 * The size in pixel of the output image.
 	 */
 	target_size?: TargetSize;
 	[property: string]: unknown;
 }
 
 /**
- * The size in pixel of the output image
+ * The size in pixel of the output image.
  */
 export interface TargetSize {
 	height: number;
@@ -60,7 +61,7 @@ export interface TargetSize {
  */
 export interface ImageToImageOutput {
 	/**
-	 * The output image
+	 * The output image returned as raw bytes in the payload.
 	 */
 	image?: unknown;
 	[property: string]: unknown;

package/src/tasks/image-to-image/spec/input.json

@@ -6,7 +6,8 @@
 	"type": "object",
 	"properties": {
 		"inputs": {
-			"description": "The input image data"
+			"type": "string",
+			"description": "The input image data as a base64-encoded string. If no `parameters` are provided, you can also provide the image data as a raw bytes payload."
 		},
 		"parameters": {
 			"description": "Additional inference parameters",
@@ -36,7 +37,7 @@
 				},
 				"target_size": {
 					"type": "object",
-					"description": "The size in pixel of the output image",
+					"description": "The size in pixel of the output image.",
 					"properties": {
 						"width": {
 							"type": "integer"

package/src/tasks/image-to-image/spec/output.json

@@ -6,7 +6,7 @@
 	"type": "object",
 	"properties": {
 		"image": {
-			"description": "The output image"
+			"description": "The output image returned as raw bytes in the payload."
 		}
 	}
 }

package/src/tasks/index.ts

@@ -73,12 +73,7 @@ export type * from "./table-question-answering/inference";
 export type { TextToImageInput, TextToImageOutput, TextToImageParameters } from "./text-to-image/inference";
 export type { TextToAudioParameters, TextToSpeechInput, TextToSpeechOutput } from "./text-to-speech/inference";
 export type * from "./token-classification/inference";
-export type {
-	Text2TextGenerationParameters,
-	Text2TextGenerationTruncationStrategy,
-	TranslationInput,
-	TranslationOutput,
-} from "./translation/inference";
+export type { TranslationInput, TranslationOutput } from "./translation/inference";
 export type {
 	ClassificationOutputTransform,
 	TextClassificationInput,
@@ -131,6 +126,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"image-to-image": ["diffusers", "transformers", "transformers.js"],
 	"image-to-text": ["transformers", "transformers.js"],
 	"image-to-video": ["diffusers"],
+	"keypoint-detection": ["transformers"],
 	"video-classification": ["transformers"],
 	"mask-generation": ["transformers"],
 	"multiple-choice": ["transformers"],
@@ -210,6 +206,7 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
 	"image-text-to-text": getData("image-text-to-text", imageTextToText),
 	"image-to-text": getData("image-to-text", imageToText),
 	"image-to-video": undefined,
+	"keypoint-detection": getData("keypoint-detection", placeholder),
 	"mask-generation": getData("mask-generation", maskGeneration),
 	"multiple-choice": undefined,
 	"object-detection": getData("object-detection", objectDetection),

package/src/tasks/keypoint-detection/about.md

@@ -0,0 +1,59 @@
+## Task Variants
+
+### Pose Estimation
+
+Pose estimation is the process of determining the position and orientation of an object or a camera in a 3D space. It is a fundamental task in computer vision and is widely used in various applications such as robotics, augmented reality, and 3D reconstruction.
+
+## Use Cases for Keypoint Detection
+
+### Facial Landmark Estimation
+
+Keypoint detection models can be used to estimate the position of facial landmarks. Facial landmarks are points on the face such as the corners of the mouth, the outer corners of the eyes, and the tip of the nose. These landmarks can be used for a variety of applications, such as facial expression recognition, 3D face reconstruction, and cinematic animation.
+
+### Fitness Tracking
+
+Keypoint detection models can be used to track the movement of the human body, e.g. position of the joints in a 3D space. This can be used for a variety of applications, such as fitness tracking, sports analysis or virtual reality applications.
+
+## Inference Code
+
+Below you can find an example of how to use a keypoint detection model and how to visualize the results.
+
+```python
+from transformers import AutoImageProcessor, SuperPointForKeypointDetection
+import torch
+import matplotlib.pyplot as plt
+from PIL import Image
+import requests
+
+url_image = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url_image_1, stream=True).raw)
+
+# initialize the model and processor
+processor = AutoImageProcessor.from_pretrained("magic-leap-community/superpoint")
+model = SuperPointForKeypointDetection.from_pretrained("magic-leap-community/superpoint")
+
+# infer
+inputs = processor(image, return_tensors="pt").to(model.device, model.dtype)
+outputs = model(**inputs)
+
+# visualize the output
+image_width, image_height = image.size
+image_mask = outputs.mask
+image_indices = torch.nonzero(image_mask).squeeze()
+
+image_scores = outputs.scores.squeeze()
+image_keypoints = outputs.keypoints.squeeze()
+keypoints = image_keypoints.detach().numpy()
+scores = image_scores.detach().numpy()
+
+plt.axis('off')
+plt.imshow(image)
+plt.scatter(
+    keypoints[:, 0],
+    keypoints[:, 1],
+    s=scores * 100,
+    c='cyan',
+    alpha=0.4
+)
+plt.show()
+```

package/src/tasks/keypoint-detection/data.ts

@@ -0,0 +1,46 @@
+import type { TaskDataCustom } from "..";
+
+const taskData: TaskDataCustom = {
+	datasets: [
+		{
+			description: "A dataset of hand keypoints of over 500k examples.",
+			id: "Vincent-luo/hagrid-mediapipe-hands",
+		},
+	],
+	demo: {
+		inputs: [
+			{
+				filename: "keypoint-detection-input.png",
+				type: "img",
+			},
+		],
+		outputs: [
+			{
+				filename: "keypoint-detection-output.png",
+				type: "img",
+			},
+		],
+	},
+	metrics: [],
+	models: [
+		{
+			description: "A robust keypoint detection model.",
+			id: "magic-leap-community/superpoint",
+		},
+		{
+			description: "Strong keypoint detection model used to detect human pose.",
+			id: "qualcomm/MediaPipe-Pose-Estimation",
+		},
+	],
+	spaces: [
+		{
+			description: "An application that detects hand keypoints in real-time.",
+			id: "datasciencedojo/Hand-Keypoint-Detection-Realtime",
+		},
+	],
+	summary: "Keypoint detection is the task of identifying meaningful distinctive points or features in an image.",
+	widgetModels: [],
+	youtubeId: "",
+};
+
+export default taskData;