@huggingface/tasks 0.11.3 → 0.11.4

package/dist/index.cjs

@@ -1617,7 +1617,10 @@ var data_default3 = taskData3;
 var taskData4 = {
   datasets: [
     {
-      // TODO write proper description
+      description: "Largest document understanding dataset.",
+      id: "HuggingFaceM4/Docmatix"
+    },
+    {
       description: "Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
       id: "eliolio/docvqa"
     }
@@ -1658,8 +1661,8 @@ var taskData4 = {
       id: "impira/layoutlm-document-qa"
     },
     {
-      description: "A special model for OCR-free Document QA task. Donut model fine-tuned on DocVQA.",
-      id: "naver-clova-ix/donut-base-finetuned-docvqa"
+      description: "A special model for OCR-free Document QA task.",
+      id: "microsoft/udop-large"
     },
     {
       description: "A powerful model for document question answering.",
@@ -1939,6 +1942,10 @@ var taskData8 = {
     {
       description: "A robust image feature extraction models.",
       id: "facebook/dino-vitb16"
+    },
+    {
+      description: "Strong image-text-to-text model made for information retrieval from documents.",
+      id: "vidore/colpali"
     }
   ],
   spaces: [],
@@ -2165,8 +2172,8 @@ var taskData11 = {
   metrics: [],
   models: [
     {
-      description: "Cutting-edge vision language model that can also localize texts in images.",
-      id: "liuhaotian/llava-v1.6-34b"
+      description: "Cutting-edge vision language model that can take multiple image inputs.",
+      id: "facebook/chameleon-7b"
     },
     {
       description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
@@ -2179,6 +2186,10 @@ var taskData11 = {
     {
       description: "Strong image-text-to-text model made to understand documents.",
       id: "mPLUG/DocOwl1.5"
+    },
+    {
+      description: "Strong image-text-to-text model.",
+      id: "llava-hf/llava-v1.6-mistral-7b-hf"
     }
   ],
   spaces: [
@@ -6626,6 +6637,12 @@ var DATASET_LIBRARIES_UI_ELEMENTS = {
     repoName: "argilla",
     repoUrl: "https://github.com/argilla-io/argilla",
     docsUrl: "https://argilla-io.github.io/argilla"
+  },
+  polars: {
+    prettyLabel: "Polars",
+    repoName: "polars",
+    repoUrl: "https://github.com/pola-rs/polars",
+    docsUrl: "https://docs.pola.rs/"
   }
 };
 // Annotate the CommonJS export names for ESM import in node:

package/dist/index.js

@@ -1579,7 +1579,10 @@ var data_default3 = taskData3;
 var taskData4 = {
   datasets: [
     {
-      // TODO write proper description
+      description: "Largest document understanding dataset.",
+      id: "HuggingFaceM4/Docmatix"
+    },
+    {
       description: "Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
       id: "eliolio/docvqa"
     }
@@ -1620,8 +1623,8 @@ var taskData4 = {
       id: "impira/layoutlm-document-qa"
     },
     {
-      description: "A special model for OCR-free Document QA task. Donut model fine-tuned on DocVQA.",
-      id: "naver-clova-ix/donut-base-finetuned-docvqa"
+      description: "A special model for OCR-free Document QA task.",
+      id: "microsoft/udop-large"
     },
     {
       description: "A powerful model for document question answering.",
@@ -1901,6 +1904,10 @@ var taskData8 = {
     {
       description: "A robust image feature extraction models.",
       id: "facebook/dino-vitb16"
+    },
+    {
+      description: "Strong image-text-to-text model made for information retrieval from documents.",
+      id: "vidore/colpali"
     }
   ],
   spaces: [],
@@ -2127,8 +2134,8 @@ var taskData11 = {
   metrics: [],
   models: [
     {
-      description: "Cutting-edge vision language model that can also localize texts in images.",
-      id: "liuhaotian/llava-v1.6-34b"
+      description: "Cutting-edge vision language model that can take multiple image inputs.",
+      id: "facebook/chameleon-7b"
     },
     {
       description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
@@ -2141,6 +2148,10 @@ var taskData11 = {
     {
       description: "Strong image-text-to-text model made to understand documents.",
       id: "mPLUG/DocOwl1.5"
+    },
+    {
+      description: "Strong image-text-to-text model.",
+      id: "llava-hf/llava-v1.6-mistral-7b-hf"
     }
   ],
   spaces: [
@@ -6588,6 +6599,12 @@ var DATASET_LIBRARIES_UI_ELEMENTS = {
     repoName: "argilla",
     repoUrl: "https://github.com/argilla-io/argilla",
     docsUrl: "https://argilla-io.github.io/argilla"
+  },
+  polars: {
+    prettyLabel: "Polars",
+    repoName: "polars",
+    repoUrl: "https://github.com/pola-rs/polars",
+    docsUrl: "https://docs.pola.rs/"
   }
 };
 export {

package/dist/src/dataset-libraries.d.ts

@@ -70,6 +70,12 @@ export declare const DATASET_LIBRARIES_UI_ELEMENTS: {
         repoUrl: string;
         docsUrl: string;
     };
+    polars: {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        docsUrl: string;
+    };
 };
 export type DatasetLibraryKey = keyof typeof DATASET_LIBRARIES_UI_ELEMENTS;
 //# sourceMappingURL=dataset-libraries.d.ts.map

package/dist/src/dataset-libraries.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"dataset-libraries.d.ts","sourceRoot":"","sources":["../../src/dataset-libraries.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,MAAM,WAAW,uBAAuB;IACvC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,eAAO,MAAM,6BAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAiDS,CAAC;AAGpD,MAAM,MAAM,iBAAiB,GAAG,MAAM,OAAO,6BAA6B,CAAC"}
+{"version":3,"file":"dataset-libraries.d.ts","sourceRoot":"","sources":["../../src/dataset-libraries.ts"],"names":[],"mappings":"AAAA;;GAEG;AACH,MAAM,WAAW,uBAAuB;IACvC;;;;OAIG;IACH,WAAW,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAC;IACjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;CACjB;AAED,eAAO,MAAM,6BAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAuDS,CAAC;AAGpD,MAAM,MAAM,iBAAiB,GAAG,MAAM,OAAO,6BAA6B,CAAC"}

package/dist/src/tasks/document-question-answering/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/document-question-answering/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAyEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/document-question-answering/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA4Ef,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/src/tasks/image-feature-extraction/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-feature-extraction/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cA8Cf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-feature-extraction/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAkDf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/src/tasks/image-text-to-text/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAqFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-text-to-text/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,IAAI,CAAC;AAEzC,QAAA,MAAM,QAAQ,EAAE,cAyFf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.11.3",
+  "version": "0.11.4",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/dataset-libraries.ts

@@ -71,6 +71,12 @@ export const DATASET_LIBRARIES_UI_ELEMENTS = {
 		repoUrl: "https://github.com/argilla-io/argilla",
 		docsUrl: "https://argilla-io.github.io/argilla",
 	},
+	polars: {
+		prettyLabel: "Polars",
+		repoName: "polars",
+		repoUrl: "https://github.com/pola-rs/polars",
+		docsUrl: "https://docs.pola.rs/",
+	},
 } satisfies Record<string, DatasetLibraryUiElement>;
 
 /// List of the dataset libraries supported by the Hub

package/src/tasks/document-question-answering/data.ts

@@ -3,7 +3,10 @@ import type { TaskDataCustom } from "..";
 const taskData: TaskDataCustom = {
 	datasets: [
 		{
-			// TODO write proper description
+			description: "Largest document understanding dataset.",
+			id: "HuggingFaceM4/Docmatix",
+		},
+		{
 			description:
 				"Dataset from the 2020 DocVQA challenge. The documents are taken from the UCSF Industry Documents Library.",
 			id: "eliolio/docvqa",
@@ -47,8 +50,8 @@ const taskData: TaskDataCustom = {
 			id: "impira/layoutlm-document-qa",
 		},
 		{
-			description: "A special model for OCR-free Document QA task. Donut model fine-tuned on DocVQA.",
-			id: "naver-clova-ix/donut-base-finetuned-docvqa",
+			description: "A special model for OCR-free Document QA task.",
+			id: "microsoft/udop-large",
 		},
 		{
 			description: "A powerful model for document question answering.",

package/src/tasks/image-feature-extraction/data.ts

@@ -42,6 +42,10 @@ const taskData: TaskDataCustom = {
 			description: "A robust image feature extraction models.",
 			id: "facebook/dino-vitb16",
 		},
+		{
+			description: "Strong image-text-to-text model made for information retrieval from documents.",
+			id: "vidore/colpali",
+		},
 	],
 	spaces: [],
 	summary: "Image feature extraction is the task of extracting features learnt in a computer vision model.",

package/src/tasks/image-text-to-text/data.ts

@@ -43,8 +43,8 @@ const taskData: TaskDataCustom = {
 	metrics: [],
 	models: [
 		{
-			description: "Cutting-edge vision language model that can also localize texts in images.",
-			id: "liuhaotian/llava-v1.6-34b",
+			description: "Cutting-edge vision language model that can take multiple image inputs.",
+			id: "facebook/chameleon-7b",
 		},
 		{
 			description: "Cutting-edge conversational vision language model that can take multiple image inputs.",
@@ -58,6 +58,10 @@ const taskData: TaskDataCustom = {
 			description: "Strong image-text-to-text model made to understand documents.",
 			id: "mPLUG/DocOwl1.5",
 		},
+		{
+			description: "Strong image-text-to-text model.",
+			id: "llava-hf/llava-v1.6-mistral-7b-hf",
+		},
 	],
 	spaces: [
 		{