@huggingface/tasks 0.19.15 → 0.19.17

package/src/pipelines.ts

@@ -43,10 +43,6 @@ export interface PipelineData {
 	name: string;
 	subtasks?: SubTask[];
 	modality: Modality;
-	/**
-	 * color for the tag icon.
-	 */
-	color: "blue" | "green" | "indigo" | "orange" | "red" | "yellow";
 	/**
 	 * whether to hide in /models filters
 	 */
@@ -143,7 +139,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "orange",
 	},
 	"token-classification": {
 		name: "Token Classification",
@@ -174,12 +169,10 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "blue",
 	},
 	"table-question-answering": {
 		name: "Table Question Answering",
 		modality: "nlp",
-		color: "green",
 	},
 	"question-answering": {
 		name: "Question Answering",
@@ -198,17 +191,14 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "blue",
 	},
 	"zero-shot-classification": {
 		name: "Zero-Shot Classification",
 		modality: "nlp",
-		color: "yellow",
 	},
 	translation: {
 		name: "Translation",
 		modality: "nlp",
-		color: "green",
 	},
 	summarization: {
 		name: "Summarization",
@@ -223,12 +213,10 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "indigo",
 	},
 	"feature-extraction": {
 		name: "Feature Extraction",
 		modality: "nlp",
-		color: "red",
 	},
 	"text-generation": {
 		name: "Text Generation",
@@ -251,7 +239,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "indigo",
 	},
 	"text2text-generation": {
 		name: "Text2Text Generation",
@@ -286,7 +273,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "indigo",
 	},
 	"fill-mask": {
 		name: "Fill-Mask",
@@ -301,32 +287,26 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "red",
 	},
 	"sentence-similarity": {
 		name: "Sentence Similarity",
 		modality: "nlp",
-		color: "yellow",
 	},
 	"text-to-speech": {
 		name: "Text-to-Speech",
 		modality: "audio",
-		color: "yellow",
 	},
 	"text-to-audio": {
 		name: "Text-to-Audio",
 		modality: "audio",
-		color: "yellow",
 	},
 	"automatic-speech-recognition": {
 		name: "Automatic Speech Recognition",
 		modality: "audio",
-		color: "yellow",
 	},
 	"audio-to-audio": {
 		name: "Audio-to-Audio",
 		modality: "audio",
-		color: "blue",
 	},
 	"audio-classification": {
 		name: "Audio Classification",
@@ -353,23 +333,19 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "audio",
-		color: "green",
 	},
 	"audio-text-to-text": {
 		name: "Audio-Text-to-Text",
 		modality: "multimodal",
-		color: "red",
 		hideInDatasets: true,
 	},
 	"voice-activity-detection": {
 		name: "Voice Activity Detection",
 		modality: "audio",
-		color: "red",
 	},
 	"depth-estimation": {
 		name: "Depth Estimation",
 		modality: "cv",
-		color: "yellow",
 	},
 	"image-classification": {
 		name: "Image Classification",
@@ -384,7 +360,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "blue",
 	},
 	"object-detection": {
 		name: "Object Detection",
@@ -399,7 +374,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "yellow",
 	},
 	"image-segmentation": {
 		name: "Image Segmentation",
@@ -418,12 +392,10 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "green",
 	},
 	"text-to-image": {
 		name: "Text-to-Image",
 		modality: "cv",
-		color: "yellow",
 	},
 	"image-to-text": {
 		name: "Image-to-Text",
@@ -434,7 +406,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "red",
 	},
 	"image-to-image": {
 		name: "Image-to-Image",
@@ -453,27 +424,22 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "indigo",
 	},
 	"image-to-video": {
 		name: "Image-to-Video",
 		modality: "cv",
-		color: "indigo",
 	},
 	"unconditional-image-generation": {
 		name: "Unconditional Image Generation",
 		modality: "cv",
-		color: "green",
 	},
 	"video-classification": {
 		name: "Video Classification",
 		modality: "cv",
-		color: "blue",
 	},
 	"reinforcement-learning": {
 		name: "Reinforcement Learning",
 		modality: "rl",
-		color: "red",
 	},
 	robotics: {
 		name: "Robotics",
@@ -488,7 +454,6 @@ export const PIPELINE_DATA = {
 				name: "Task Planning",
 			},
 		],
-		color: "blue",
 	},
 	"tabular-classification": {
 		name: "Tabular Classification",
@@ -503,7 +468,6 @@ export const PIPELINE_DATA = {
 				name: "Tabular Multi Label Classification",
 			},
 		],
-		color: "blue",
 	},
 	"tabular-regression": {
 		name: "Tabular Regression",
@@ -514,7 +478,6 @@ export const PIPELINE_DATA = {
 				name: "Tabular Single Column Regression",
 			},
 		],
-		color: "blue",
 	},
 	"tabular-to-text": {
 		name: "Tabular to Text",
@@ -525,13 +488,11 @@ export const PIPELINE_DATA = {
 				name: "RDF to text",
 			},
 		],
-		color: "blue",
 		hideInModels: true,
 	},
 	"table-to-text": {
 		name: "Table to Text",
 		modality: "nlp",
-		color: "blue",
 		hideInModels: true,
 	},
 	"multiple-choice": {
@@ -547,13 +508,11 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "blue",
 		hideInModels: true,
 	},
 	"text-ranking": {
 		name: "Text Ranking",
 		modality: "nlp",
-		color: "red",
 	},
 	"text-retrieval": {
 		name: "Text Retrieval",
@@ -576,7 +535,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "nlp",
-		color: "indigo",
 		hideInModels: true,
 	},
 	"time-series-forecasting": {
@@ -592,18 +550,14 @@ export const PIPELINE_DATA = {
 				name: "Multivariate Time Series Forecasting",
 			},
 		],
-		color: "blue",
 	},
 	"text-to-video": {
 		name: "Text-to-Video",
 		modality: "cv",
-		color: "green",
 	},
 	"image-text-to-text": {
 		name: "Image-Text-to-Text",
 		modality: "multimodal",
-		color: "red",
-		hideInDatasets: true,
 	},
 	"visual-question-answering": {
 		name: "Visual Question Answering",
@@ -614,7 +568,6 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "multimodal",
-		color: "red",
 	},
 	"document-question-answering": {
 		name: "Document Question Answering",
@@ -625,48 +578,39 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "multimodal",
-		color: "blue",
 		hideInDatasets: true,
 	},
 	"zero-shot-image-classification": {
 		name: "Zero-Shot Image Classification",
 		modality: "cv",
-		color: "yellow",
 	},
 	"graph-ml": {
 		name: "Graph Machine Learning",
 		modality: "other",
-		color: "green",
 	},
 	"mask-generation": {
 		name: "Mask Generation",
 		modality: "cv",
-		color: "indigo",
 	},
 	"zero-shot-object-detection": {
 		name: "Zero-Shot Object Detection",
 		modality: "cv",
-		color: "yellow",
 	},
 	"text-to-3d": {
 		name: "Text-to-3D",
 		modality: "cv",
-		color: "yellow",
 	},
 	"image-to-3d": {
 		name: "Image-to-3D",
 		modality: "cv",
-		color: "green",
 	},
 	"image-feature-extraction": {
 		name: "Image Feature Extraction",
 		modality: "cv",
-		color: "indigo",
 	},
 	"video-text-to-text": {
 		name: "Video-Text-to-Text",
 		modality: "multimodal",
-		color: "blue",
 		hideInDatasets: false,
 	},
 	"keypoint-detection": {
@@ -678,25 +622,24 @@ export const PIPELINE_DATA = {
 			},
 		],
 		modality: "cv",
-		color: "red",
 		hideInDatasets: true,
 	},
 	"visual-document-retrieval": {
 		name: "Visual Document Retrieval",
 		modality: "multimodal",
-		color: "yellow",
-		hideInDatasets: true,
 	},
 	"any-to-any": {
 		name: "Any-to-Any",
 		modality: "multimodal",
-		color: "yellow",
+	},
+	"video-to-video": {
+		name: "Video-to-Video",
+		modality: "cv",
 		hideInDatasets: true,
 	},
 	other: {
 		name: "Other",
 		modality: "other",
-		color: "blue",
 		hideInModels: true,
 		hideInDatasets: true,
 	},

package/src/tasks/index.ts

@@ -113,7 +113,6 @@ export type {
 } from "./zero-shot-object-detection/inference.js";
 
 import type { ModelLibraryKey } from "../model-libraries.js";
-
 /**
  * Model libraries compatible with each ML task
  */
@@ -181,6 +180,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"image-to-3d": ["diffusers"],
 	"any-to-any": ["transformers"],
 	"visual-document-retrieval": ["transformers"],
+	"video-to-video": ["diffusers"],
 };
 
 /**
@@ -250,6 +250,7 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
 	translation: getData("translation", translation),
 	"unconditional-image-generation": getData("unconditional-image-generation", unconditionalImageGeneration),
 	"video-text-to-text": getData("video-text-to-text", videoTextToText),
+	"video-to-video": getData("video-to-video", placeholder),
 	"visual-question-answering": getData("visual-question-answering", visualQuestionAnswering),
 	"voice-activity-detection": undefined,
 	"zero-shot-classification": getData("zero-shot-classification", zeroShotClassification),

package/src/tasks/placeholder/spec/output.json

@@ -9,7 +9,7 @@
 		"properties": {
 			"meaningful_output_name": {
 				"type": "string",
-				"description": "TODO: Describe what is outputed by the inference here"
+				"description": "TODO: Describe what is outputted by the inference here"
 			}
 		},
 		"required": ["meaningfulOutputName"]

package/src/tasks/reinforcement-learning/about.md

@@ -48,7 +48,7 @@ Observations and states are the information our agent gets from the environment.
 
 Inference in reinforcement learning differs from other modalities, in which there's a model and test data. In reinforcement learning, once you have trained an agent in an environment, you try to run the trained agent for additional steps to get the average reward.
 
-A typical training cycle consists of gathering experience from the environment, training the agent, and running the agent on a test environment to obtain average reward. Below there's a snippet on how you can interact with the environment using the `gymnasium` library, train an agent using `stable-baselines3`, evalute the agent on test environment and infer actions from the trained agent.
+A typical training cycle consists of gathering experience from the environment, training the agent, and running the agent on a test environment to obtain average reward. Below there's a snippet on how you can interact with the environment using the `gymnasium` library, train an agent using `stable-baselines3`, evaluate the agent on test environment and infer actions from the trained agent.
 
 ```python
 # Here we are running 20 episodes of CartPole-v1 environment, taking random actions

package/src/tasks/text-generation/about.md

@@ -101,7 +101,7 @@ Would you like to learn more about the topic? Awesome! Here you can find some cu
 
 - You can use [PEFT](https://github.com/huggingface/peft) to adapt large language models in efficient way.
 - [ChatUI](https://github.com/huggingface/chat-ui) is the open-source interface to conversate with Large Language Models.
-- [text-generation-inferface](https://github.com/huggingface/text-generation-inference)
+- [text-generation-inference](https://github.com/huggingface/text-generation-inference)
 - [HuggingChat](https://huggingface.co/chat/) is a chat interface powered by Hugging Face to chat with powerful models like Meta Llama 3 70B, Mixtral 8x7B, etc.
 
 ### Documentation