@huggingface/tasks 0.3.0 → 0.3.1

package/dist/index.cjs

@@ -942,7 +942,7 @@ var PIPELINE_DATA = {
   },
   "feature-extraction": {
     name: "Feature Extraction",
-    modality: "multimodal",
+    modality: "nlp",
     color: "red"
   },
   "text-generation": {
@@ -1123,7 +1123,7 @@ var PIPELINE_DATA = {
   },
   "text-to-image": {
     name: "Text-to-Image",
-    modality: "multimodal",
+    modality: "cv",
     color: "yellow"
   },
   "image-to-text": {
@@ -1134,7 +1134,7 @@ var PIPELINE_DATA = {
         name: "Image Captioning"
       }
     ],
-    modality: "multimodal",
+    modality: "cv",
     color: "red"
   },
   "image-to-image": {
@@ -1158,7 +1158,7 @@ var PIPELINE_DATA = {
   },
   "image-to-video": {
     name: "Image-to-Video",
-    modality: "multimodal",
+    modality: "cv",
     color: "indigo"
   },
   "unconditional-image-generation": {
@@ -1293,9 +1293,15 @@ var PIPELINE_DATA = {
   },
   "text-to-video": {
     name: "Text-to-Video",
-    modality: "multimodal",
+    modality: "cv",
     color: "green"
   },
+  "image-text-to-text": {
+    name: "Image + Text to Image (VLLMs)",
+    modality: "multimodal",
+    color: "red",
+    hideInDatasets: true
+  },
   "visual-question-answering": {
     name: "Visual Question Answering",
     subtasks: [
@@ -1326,7 +1332,7 @@ var PIPELINE_DATA = {
   },
   "graph-ml": {
     name: "Graph Machine Learning",
-    modality: "multimodal",
+    modality: "other",
     color: "green"
   },
   "mask-generation": {
@@ -1341,12 +1347,12 @@ var PIPELINE_DATA = {
   },
   "text-to-3d": {
     name: "Text-to-3D",
-    modality: "multimodal",
+    modality: "cv",
     color: "yellow"
   },
   "image-to-3d": {
     name: "Image-to-3D",
-    modality: "multimodal",
+    modality: "cv",
     color: "green"
   },
   other: {
@@ -3908,6 +3914,7 @@ var TASKS_MODEL_LIBRARIES = {
   "graph-ml": ["transformers"],
   "image-classification": ["keras", "timm", "transformers", "transformers.js"],
   "image-segmentation": ["transformers", "transformers.js"],
+  "image-text-to-text": ["transformers"],
   "image-to-image": ["diffusers", "transformers", "transformers.js"],
   "image-to-text": ["transformers", "transformers.js"],
   "image-to-video": ["diffusers"],
@@ -3974,6 +3981,7 @@ var TASKS_DATA = {
   "graph-ml": void 0,
   "image-classification": getData("image-classification", data_default8),
   "image-segmentation": getData("image-segmentation", data_default11),
+  "image-text-to-text": void 0,
   "image-to-image": getData("image-to-image", data_default9),
   "image-to-text": getData("image-to-text", data_default10),
   "image-to-video": void 0,

package/dist/index.d.ts

@@ -115,7 +115,7 @@ declare const PIPELINE_DATA: {
     };
     "feature-extraction": {
         name: string;
-        modality: "multimodal";
+        modality: "nlp";
         color: "red";
     };
     "text-generation": {
@@ -218,7 +218,7 @@ declare const PIPELINE_DATA: {
     };
     "text-to-image": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "yellow";
     };
     "image-to-text": {
@@ -227,7 +227,7 @@ declare const PIPELINE_DATA: {
             type: string;
             name: string;
         }[];
-        modality: "multimodal";
+        modality: "cv";
         color: "red";
     };
     "image-to-image": {
@@ -241,7 +241,7 @@ declare const PIPELINE_DATA: {
     };
     "image-to-video": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "indigo";
     };
     "unconditional-image-generation": {
@@ -334,9 +334,15 @@ declare const PIPELINE_DATA: {
     };
     "text-to-video": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "green";
     };
+    "image-text-to-text": {
+        name: string;
+        modality: "multimodal";
+        color: "red";
+        hideInDatasets: true;
+    };
     "visual-question-answering": {
         name: string;
         subtasks: {
@@ -363,7 +369,7 @@ declare const PIPELINE_DATA: {
     };
     "graph-ml": {
         name: string;
-        modality: "multimodal";
+        modality: "other";
         color: "green";
     };
     "mask-generation": {
@@ -378,12 +384,12 @@ declare const PIPELINE_DATA: {
     };
     "text-to-3d": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "yellow";
     };
     "image-to-3d": {
         name: string;
-        modality: "multimodal";
+        modality: "cv";
         color: "green";
     };
     other: {
@@ -395,9 +401,9 @@ declare const PIPELINE_DATA: {
     };
 };
 type PipelineType = keyof typeof PIPELINE_DATA;
-declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d")[];
+declare const PIPELINE_TYPES: ("other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d")[];
 declare const SUBTASK_TYPES: string[];
-declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d">;
+declare const PIPELINE_TYPES_SET: Set<"other" | "text-classification" | "token-classification" | "table-question-answering" | "question-answering" | "zero-shot-classification" | "translation" | "summarization" | "conversational" | "feature-extraction" | "text-generation" | "text2text-generation" | "fill-mask" | "sentence-similarity" | "text-to-speech" | "text-to-audio" | "automatic-speech-recognition" | "audio-to-audio" | "audio-classification" | "voice-activity-detection" | "depth-estimation" | "image-classification" | "object-detection" | "image-segmentation" | "text-to-image" | "image-to-text" | "image-to-image" | "image-to-video" | "unconditional-image-generation" | "video-classification" | "reinforcement-learning" | "robotics" | "tabular-classification" | "tabular-regression" | "tabular-to-text" | "table-to-text" | "multiple-choice" | "text-retrieval" | "time-series-forecasting" | "text-to-video" | "image-text-to-text" | "visual-question-answering" | "document-question-answering" | "zero-shot-image-classification" | "graph-ml" | "mask-generation" | "zero-shot-object-detection" | "text-to-3d" | "image-to-3d">;
 
 /**
  * See default-widget-inputs.ts for the default widget inputs, this files only contains the types

package/dist/index.js

@@ -908,7 +908,7 @@ var PIPELINE_DATA = {
   },
   "feature-extraction": {
     name: "Feature Extraction",
-    modality: "multimodal",
+    modality: "nlp",
     color: "red"
   },
   "text-generation": {
@@ -1089,7 +1089,7 @@ var PIPELINE_DATA = {
   },
   "text-to-image": {
     name: "Text-to-Image",
-    modality: "multimodal",
+    modality: "cv",
     color: "yellow"
   },
   "image-to-text": {
@@ -1100,7 +1100,7 @@ var PIPELINE_DATA = {
         name: "Image Captioning"
       }
     ],
-    modality: "multimodal",
+    modality: "cv",
     color: "red"
   },
   "image-to-image": {
@@ -1124,7 +1124,7 @@ var PIPELINE_DATA = {
   },
   "image-to-video": {
     name: "Image-to-Video",
-    modality: "multimodal",
+    modality: "cv",
     color: "indigo"
   },
   "unconditional-image-generation": {
@@ -1259,9 +1259,15 @@ var PIPELINE_DATA = {
   },
   "text-to-video": {
     name: "Text-to-Video",
-    modality: "multimodal",
+    modality: "cv",
     color: "green"
   },
+  "image-text-to-text": {
+    name: "Image + Text to Image (VLLMs)",
+    modality: "multimodal",
+    color: "red",
+    hideInDatasets: true
+  },
   "visual-question-answering": {
     name: "Visual Question Answering",
     subtasks: [
@@ -1292,7 +1298,7 @@ var PIPELINE_DATA = {
   },
   "graph-ml": {
     name: "Graph Machine Learning",
-    modality: "multimodal",
+    modality: "other",
     color: "green"
   },
   "mask-generation": {
@@ -1307,12 +1313,12 @@ var PIPELINE_DATA = {
   },
   "text-to-3d": {
     name: "Text-to-3D",
-    modality: "multimodal",
+    modality: "cv",
     color: "yellow"
   },
   "image-to-3d": {
     name: "Image-to-3D",
-    modality: "multimodal",
+    modality: "cv",
     color: "green"
   },
   other: {
@@ -3874,6 +3880,7 @@ var TASKS_MODEL_LIBRARIES = {
   "graph-ml": ["transformers"],
   "image-classification": ["keras", "timm", "transformers", "transformers.js"],
   "image-segmentation": ["transformers", "transformers.js"],
+  "image-text-to-text": ["transformers"],
   "image-to-image": ["diffusers", "transformers", "transformers.js"],
   "image-to-text": ["transformers", "transformers.js"],
   "image-to-video": ["diffusers"],
@@ -3940,6 +3947,7 @@ var TASKS_DATA = {
   "graph-ml": void 0,
   "image-classification": getData("image-classification", data_default8),
   "image-segmentation": getData("image-segmentation", data_default11),
+  "image-text-to-text": void 0,
   "image-to-image": getData("image-to-image", data_default9),
   "image-to-text": getData("image-to-text", data_default10),
   "image-to-video": void 0,

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/pipelines.ts

@@ -238,7 +238,7 @@ export const PIPELINE_DATA = {
 	},
 	"feature-extraction": {
 		name: "Feature Extraction",
-		modality: "multimodal",
+		modality: "nlp",
 		color: "red",
 	},
 	"text-generation": {
@@ -419,7 +419,7 @@ export const PIPELINE_DATA = {
 	},
 	"text-to-image": {
 		name: "Text-to-Image",
-		modality: "multimodal",
+		modality: "cv",
 		color: "yellow",
 	},
 	"image-to-text": {
@@ -430,7 +430,7 @@ export const PIPELINE_DATA = {
 				name: "Image Captioning",
 			},
 		],
-		modality: "multimodal",
+		modality: "cv",
 		color: "red",
 	},
 	"image-to-image": {
@@ -454,7 +454,7 @@ export const PIPELINE_DATA = {
 	},
 	"image-to-video": {
 		name: "Image-to-Video",
-		modality: "multimodal",
+		modality: "cv",
 		color: "indigo",
 	},
 	"unconditional-image-generation": {
@@ -589,9 +589,15 @@ export const PIPELINE_DATA = {
 	},
 	"text-to-video": {
 		name: "Text-to-Video",
-		modality: "multimodal",
+		modality: "cv",
 		color: "green",
 	},
+	"image-text-to-text": {
+		name: "Image + Text to Image (VLLMs)",
+		modality: "multimodal",
+		color: "red",
+		hideInDatasets: true,
+	},
 	"visual-question-answering": {
 		name: "Visual Question Answering",
 		subtasks: [
@@ -622,7 +628,7 @@ export const PIPELINE_DATA = {
 	},
 	"graph-ml": {
 		name: "Graph Machine Learning",
-		modality: "multimodal",
+		modality: "other",
 		color: "green",
 	},
 	"mask-generation": {
@@ -637,12 +643,12 @@ export const PIPELINE_DATA = {
 	},
 	"text-to-3d": {
 		name: "Text-to-3D",
-		modality: "multimodal",
+		modality: "cv",
 		color: "yellow",
 	},
 	"image-to-3d": {
 		name: "Image-to-3D",
-		modality: "multimodal",
+		modality: "cv",
 		color: "green",
 	},
 	other: {

package/src/tasks/index.ts

@@ -53,6 +53,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"graph-ml": ["transformers"],
 	"image-classification": ["keras", "timm", "transformers", "transformers.js"],
 	"image-segmentation": ["transformers", "transformers.js"],
+	"image-text-to-text": ["transformers"],
 	"image-to-image": ["diffusers", "transformers", "transformers.js"],
 	"image-to-text": ["transformers", "transformers.js"],
 	"image-to-video": ["diffusers"],
@@ -130,6 +131,7 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
 	"graph-ml": undefined,
 	"image-classification": getData("image-classification", imageClassification),
 	"image-segmentation": getData("image-segmentation", imageSegmentation),
+	"image-text-to-text": undefined,
 	"image-to-image": getData("image-to-image", imageToImage),
 	"image-to-text": getData("image-to-text", imageToText),
 	"image-to-video": undefined,