@huggingface/tasks 0.15.6 → 0.15.7

package/dist/commonjs/hardware.d.ts

@@ -1,6 +1,6 @@
 /**
- * Biden AI Executive Order
- * https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
+ * Biden AI Executive Order (since revoked by President Trump):
+ * https://web.archive.org/web/20250105222429/https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
  */
 export declare const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL: number;
 export declare const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY: number;

package/dist/commonjs/hardware.js

@@ -2,8 +2,8 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.SKUS = exports.DEFAULT_MEMORY_OPTIONS = exports.TFLOPS_THRESHOLD_EU_AI_ACT_MODEL_TRAINING_TOTAL = exports.TFLOPS_THRESHOLD_WHITE_HOUSE_CLUSTER = exports.TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY = exports.TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL = void 0;
 /**
- * Biden AI Executive Order
- * https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
+ * Biden AI Executive Order (since revoked by President Trump):
+ * https://web.archive.org/web/20250105222429/https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
  */
 exports.TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL = 10 ** 14;
 exports.TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY = 10 ** 11;

package/dist/commonjs/library-to-tasks.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"library-to-tasks.d.ts","sourceRoot":"","sources":["../../src/library-to-tasks.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AAC5D,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAC;AAEnD;;;;;;GAMG;AACH,eAAO,MAAM,oBAAoB,EAAE,OAAO,CAAC,MAAM,CAAC,eAAe,EAAE,YAAY,EAAE,CAAC,CAmEjF,CAAC"}
+{"version":3,"file":"library-to-tasks.d.ts","sourceRoot":"","sources":["../../src/library-to-tasks.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AAC5D,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAC;AAEnD;;;;;;GAMG;AACH,eAAO,MAAM,oBAAoB,EAAE,OAAO,CAAC,MAAM,CAAC,eAAe,EAAE,YAAY,EAAE,CAAC,CAoEjF,CAAC"}

package/dist/commonjs/library-to-tasks.js

@@ -43,7 +43,7 @@ exports.LIBRARY_TASK_MAPPING = {
         "text2text-generation",
     ],
     stanza: ["token-classification"],
-    timm: ["image-classification"],
+    timm: ["image-classification", "image-feature-extraction"],
     transformers: [
         "audio-classification",
         "automatic-speech-recognition",
@@ -52,6 +52,7 @@ exports.LIBRARY_TASK_MAPPING = {
         "feature-extraction",
         "fill-mask",
         "image-classification",
+        "image-feature-extraction",
         "image-segmentation",
         "image-to-image",
         "image-to-text",

package/dist/commonjs/model-libraries-snippets.js

@@ -1137,7 +1137,7 @@ exports.birefnet = birefnet;
 const swarmformer = (model) => [
     `from swarmformer import SwarmFormerModel
 
-model = SwarmFormerModel.from_pretrained("${model.id}", trust_remote_code=True)
+model = SwarmFormerModel.from_pretrained("${model.id}")
 `,
 ];
 exports.swarmformer = swarmformer;

package/dist/commonjs/tasks/automatic-speech-recognition/inference.d.ts

@@ -145,7 +145,7 @@ export interface AutomaticSpeechRecognitionOutputChunk {
     /**
      * The start and end timestamps corresponding with the text
      */
-    timestamps: number[];
+    timestamp: number[];
     [property: string]: unknown;
 }
 //# sourceMappingURL=inference.d.ts.map

package/dist/commonjs/tasks/automatic-speech-recognition/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/automatic-speech-recognition/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,+BAA+B;IAC/C;;;OAGG;IACH,MAAM,EAAE,IAAI,CAAC;IACb;;OAEG;IACH,UAAU,CAAC,EAAE,oCAAoC,CAAC;IAClD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,qBAAqB,CAAC,EAAE,oBAAoB,CAAC;IAC7C;;OAEG;IACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACpC;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;;;OAKG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;;;OAQG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;OAMG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,OAAO,GAAG,OAAO,CAAC;AACnD;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;;OAGG;IACH,MAAM,CAAC,EAAE,qCAAqC,EAAE,CAAC;IACjD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,WAAW,qCAAqC;IACrD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/automatic-speech-recognition/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,+BAA+B;IAC/C;;;OAGG;IACH,MAAM,EAAE,IAAI,CAAC;IACb;;OAEG;IACH,UAAU,CAAC,EAAE,oCAAoC,CAAC;IAClD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,qBAAqB,CAAC,EAAE,oBAAoB,CAAC;IAC7C;;OAEG;IACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACpC;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;;;OAKG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;;;OAQG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;OAMG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,OAAO,GAAG,OAAO,CAAC;AACnD;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;;OAGG;IACH,MAAM,CAAC,EAAE,qCAAqC,EAAE,CAAC;IACjD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,WAAW,qCAAqC;IACrD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/commonjs/tasks/feature-extraction/inference.d.ts

@@ -13,9 +13,9 @@ export type FeatureExtractionOutput = Array<number[]>;
  */
 export interface FeatureExtractionInput {
     /**
-     * The text to embed.
+     * The text or list of texts to embed.
      */
-    inputs: string;
+    inputs: FeatureExtractionInputs;
     normalize?: boolean;
     /**
      * The name of the prompt that should be used by for encoding. If not set, no prompt
@@ -34,5 +34,9 @@ export interface FeatureExtractionInput {
     truncation_direction?: FeatureExtractionInputTruncationDirection;
     [property: string]: unknown;
 }
+/**
+ * The text or list of texts to embed.
+ */
+export type FeatureExtractionInputs = string[] | string;
 export type FeatureExtractionInputTruncationDirection = "Left" | "Right";
 //# sourceMappingURL=inference.d.ts.map

package/dist/commonjs/tasks/feature-extraction/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/feature-extraction/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH,MAAM,MAAM,uBAAuB,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC;AACtD;;;;;;GAMG;AACH,MAAM,WAAW,sBAAsB;IACtC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;;;;;;;;;;OAWG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB,oBAAoB,CAAC,EAAE,yCAAyC,CAAC;IACjE,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,MAAM,yCAAyC,GAAG,MAAM,GAAG,OAAO,CAAC"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/feature-extraction/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH,MAAM,MAAM,uBAAuB,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC;AACtD;;;;;;GAMG;AACH,MAAM,WAAW,sBAAsB;IACtC;;OAEG;IACH,MAAM,EAAE,uBAAuB,CAAC;IAChC,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;;;;;;;;;;OAWG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB,oBAAoB,CAAC,EAAE,yCAAyC,CAAC;IACjE,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,uBAAuB,GAAG,MAAM,EAAE,GAAG,MAAM,CAAC;AACxD,MAAM,MAAM,yCAAyC,GAAG,MAAM,GAAG,OAAO,CAAC"}

package/dist/commonjs/tasks/image-text-to-text/data.js

@@ -59,7 +59,7 @@ const taskData = {
         },
         {
             description: "Strong image-text-to-text model.",
-            id: "Qwen/Qwen2-VL-7B-Instruct",
+            id: "Qwen/Qwen2.5-VL-7B-Instruct",
         },
         {
             description: "Image-text-to-text model with reasoning capabilities.",
@@ -97,11 +97,11 @@ const taskData = {
         },
         {
             description: "An application that detects gaze.",
-            id: "smoondream/gaze-demo",
+            id: "moondream/gaze-demo",
         },
     ],
     summary: "Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.",
-    widgetModels: ["meta-llama/Llama-3.2-11B-Vision-Instruct"],
+    widgetModels: ["Qwen/Qwen2-VL-7B-Instruct"],
     youtubeId: "IoGaGfU1CIg",
 };
 exports.default = taskData;

package/dist/commonjs/tasks/text-generation/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-generation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAgHf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-generation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA2Hf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/commonjs/tasks/text-generation/data.js

@@ -14,6 +14,10 @@ const taskData = {
             description: "Truly open-source, curated and cleaned dialogue dataset.",
             id: "HuggingFaceH4/ultrachat_200k",
         },
+        {
+            description: "A reasoning dataset.",
+            id: "open-r1/OpenThoughts-114k-math",
+        },
         {
             description: "A multilingual instruction dataset with preference ratings on responses.",
             id: "allenai/tulu-3-sft-mixture",
@@ -54,10 +58,13 @@ const taskData = {
         },
     ],
     models: [
-        {
-            description: "A text-generation model trained to follow instructions.",
+        { description: "A text-generation model trained to follow instructions.",
             id: "google/gemma-2-2b-it",
         },
+        {
+            description: "Smaller variant of one of the most powerful models.",
+            id: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+        },
         {
             description: "Very powerful text generation model trained to follow instructions.",
             id: "meta-llama/Meta-Llama-3.1-8B-Instruct",
@@ -71,13 +78,17 @@ const taskData = {
             id: "PowerInfer/SmallThinker-3B-Preview",
         },
         {
-            description: "Strong text generation model to follow instructions.",
-            id: "Qwen/Qwen2.5-7B-Instruct",
+            description: "Strong conversational model that supports very long instructions.",
+            id: "Qwen/Qwen2.5-7B-Instruct-1M",
         },
         {
             description: "Text generation model used to write code.",
             id: "Qwen/Qwen2.5-Coder-32B-Instruct",
         },
+        {
+            description: "Powerful reasoning based open large language model.",
+            id: "deepseek-ai/DeepSeek-R1",
+        },
     ],
     spaces: [
         {

package/dist/commonjs/tasks/text-to-image/inference.d.ts

@@ -26,6 +26,10 @@ export interface TextToImageParameters {
      * the text prompt, but values too high may cause saturation and other artifacts.
      */
     guidance_scale?: number;
+    /**
+     * The height in pixels of the output image
+     */
+    height?: number;
     /**
      * One prompt to guide what NOT to include in image generation.
      */
@@ -44,17 +48,9 @@ export interface TextToImageParameters {
      */
     seed?: number;
     /**
-     * The size in pixel of the output image
+     * The width in pixels of the output image
      */
-    target_size?: TargetSize;
-    [property: string]: unknown;
-}
-/**
- * The size in pixel of the output image
- */
-export interface TargetSize {
-    height: number;
-    width: number;
+    width?: number;
     [property: string]: unknown;
 }
 /**

package/dist/commonjs/tasks/text-to-image/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,WAAW,CAAC,EAAE,UAAU,CAAC;IACzB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/hardware.d.ts

@@ -1,6 +1,6 @@
 /**
- * Biden AI Executive Order
- * https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
+ * Biden AI Executive Order (since revoked by President Trump):
+ * https://web.archive.org/web/20250105222429/https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
  */
 export declare const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL: number;
 export declare const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY: number;

package/dist/esm/hardware.js

@@ -1,6 +1,6 @@
 /**
- * Biden AI Executive Order
- * https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
+ * Biden AI Executive Order (since revoked by President Trump):
+ * https://web.archive.org/web/20250105222429/https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
  */
 export const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL = 10 ** 14;
 export const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY = 10 ** 11;

package/dist/esm/library-to-tasks.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"library-to-tasks.d.ts","sourceRoot":"","sources":["../../src/library-to-tasks.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AAC5D,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAC;AAEnD;;;;;;GAMG;AACH,eAAO,MAAM,oBAAoB,EAAE,OAAO,CAAC,MAAM,CAAC,eAAe,EAAE,YAAY,EAAE,CAAC,CAmEjF,CAAC"}
+{"version":3,"file":"library-to-tasks.d.ts","sourceRoot":"","sources":["../../src/library-to-tasks.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AAC5D,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,gBAAgB,CAAC;AAEnD;;;;;;GAMG;AACH,eAAO,MAAM,oBAAoB,EAAE,OAAO,CAAC,MAAM,CAAC,eAAe,EAAE,YAAY,EAAE,CAAC,CAoEjF,CAAC"}

package/dist/esm/library-to-tasks.js

@@ -40,7 +40,7 @@ export const LIBRARY_TASK_MAPPING = {
         "text2text-generation",
     ],
     stanza: ["token-classification"],
-    timm: ["image-classification"],
+    timm: ["image-classification", "image-feature-extraction"],
     transformers: [
         "audio-classification",
         "automatic-speech-recognition",
@@ -49,6 +49,7 @@ export const LIBRARY_TASK_MAPPING = {
         "feature-extraction",
         "fill-mask",
         "image-classification",
+        "image-feature-extraction",
         "image-segmentation",
         "image-to-image",
         "image-to-text",

package/dist/esm/model-libraries-snippets.js

@@ -1070,7 +1070,7 @@ model = BiRefNet.from_pretrained("${model.id}")`,
 export const swarmformer = (model) => [
     `from swarmformer import SwarmFormerModel
 
-model = SwarmFormerModel.from_pretrained("${model.id}", trust_remote_code=True)
+model = SwarmFormerModel.from_pretrained("${model.id}")
 `,
 ];
 export const mlx = (model) => [

package/dist/esm/tasks/automatic-speech-recognition/inference.d.ts

@@ -145,7 +145,7 @@ export interface AutomaticSpeechRecognitionOutputChunk {
     /**
      * The start and end timestamps corresponding with the text
      */
-    timestamps: number[];
+    timestamp: number[];
     [property: string]: unknown;
 }
 //# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/automatic-speech-recognition/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/automatic-speech-recognition/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,+BAA+B;IAC/C;;;OAGG;IACH,MAAM,EAAE,IAAI,CAAC;IACb;;OAEG;IACH,UAAU,CAAC,EAAE,oCAAoC,CAAC;IAClD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,qBAAqB,CAAC,EAAE,oBAAoB,CAAC;IAC7C;;OAEG;IACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACpC;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;;;OAKG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;;;OAQG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;OAMG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,OAAO,GAAG,OAAO,CAAC;AACnD;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;;OAGG;IACH,MAAM,CAAC,EAAE,qCAAqC,EAAE,CAAC;IACjD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,WAAW,qCAAqC;IACrD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/automatic-speech-recognition/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,+BAA+B;IAC/C;;;OAGG;IACH,MAAM,EAAE,IAAI,CAAC;IACb;;OAEG;IACH,UAAU,CAAC,EAAE,oCAAoC,CAAC;IAClD,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oCAAoC;IACpD;;OAEG;IACH,qBAAqB,CAAC,EAAE,oBAAoB,CAAC;IAC7C;;OAEG;IACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,oBAAoB;IACpC;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;;;OAKG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;;;OAQG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf;;;;;;OAMG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,OAAO,GAAG,OAAO,CAAC;AACnD;;GAEG;AACH,MAAM,WAAW,gCAAgC;IAChD;;;OAGG;IACH,MAAM,CAAC,EAAE,qCAAqC,EAAE,CAAC;IACjD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,WAAW,qCAAqC;IACrD;;OAEG;IACH,IAAI,EAAE,MAAM,CAAC;IACb;;OAEG;IACH,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/feature-extraction/inference.d.ts

@@ -13,9 +13,9 @@ export type FeatureExtractionOutput = Array<number[]>;
  */
 export interface FeatureExtractionInput {
     /**
-     * The text to embed.
+     * The text or list of texts to embed.
      */
-    inputs: string;
+    inputs: FeatureExtractionInputs;
     normalize?: boolean;
     /**
      * The name of the prompt that should be used by for encoding. If not set, no prompt
@@ -34,5 +34,9 @@ export interface FeatureExtractionInput {
     truncation_direction?: FeatureExtractionInputTruncationDirection;
     [property: string]: unknown;
 }
+/**
+ * The text or list of texts to embed.
+ */
+export type FeatureExtractionInputs = string[] | string;
 export type FeatureExtractionInputTruncationDirection = "Left" | "Right";
 //# sourceMappingURL=inference.d.ts.map

package/dist/esm/tasks/feature-extraction/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/feature-extraction/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH,MAAM,MAAM,uBAAuB,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC;AACtD;;;;;;GAMG;AACH,MAAM,WAAW,sBAAsB;IACtC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;;;;;;;;;;OAWG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB,oBAAoB,CAAC,EAAE,yCAAyC,CAAC;IACjE,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD,MAAM,MAAM,yCAAyC,GAAG,MAAM,GAAG,OAAO,CAAC"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/feature-extraction/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH,MAAM,MAAM,uBAAuB,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC;AACtD;;;;;;GAMG;AACH,MAAM,WAAW,sBAAsB;IACtC;;OAEG;IACH,MAAM,EAAE,uBAAuB,CAAC;IAChC,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;;;;;;;;;;OAWG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB,oBAAoB,CAAC,EAAE,yCAAyC,CAAC;IACjE,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,MAAM,uBAAuB,GAAG,MAAM,EAAE,GAAG,MAAM,CAAC;AACxD,MAAM,MAAM,yCAAyC,GAAG,MAAM,GAAG,OAAO,CAAC"}

package/dist/esm/tasks/image-text-to-text/data.js

@@ -57,7 +57,7 @@ const taskData = {
         },
         {
             description: "Strong image-text-to-text model.",
-            id: "Qwen/Qwen2-VL-7B-Instruct",
+            id: "Qwen/Qwen2.5-VL-7B-Instruct",
         },
         {
             description: "Image-text-to-text model with reasoning capabilities.",
@@ -95,11 +95,11 @@ const taskData = {
         },
         {
             description: "An application that detects gaze.",
-            id: "smoondream/gaze-demo",
+            id: "moondream/gaze-demo",
         },
     ],
     summary: "Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.",
-    widgetModels: ["meta-llama/Llama-3.2-11B-Vision-Instruct"],
+    widgetModels: ["Qwen/Qwen2-VL-7B-Instruct"],
     youtubeId: "IoGaGfU1CIg",
 };
 export default taskData;

package/dist/esm/tasks/text-generation/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-generation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAgHf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-generation/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA2Hf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/text-generation/data.js

@@ -12,6 +12,10 @@ const taskData = {
             description: "Truly open-source, curated and cleaned dialogue dataset.",
             id: "HuggingFaceH4/ultrachat_200k",
         },
+        {
+            description: "A reasoning dataset.",
+            id: "open-r1/OpenThoughts-114k-math",
+        },
         {
             description: "A multilingual instruction dataset with preference ratings on responses.",
             id: "allenai/tulu-3-sft-mixture",
@@ -52,10 +56,13 @@ const taskData = {
         },
     ],
     models: [
-        {
-            description: "A text-generation model trained to follow instructions.",
+        { description: "A text-generation model trained to follow instructions.",
             id: "google/gemma-2-2b-it",
         },
+        {
+            description: "Smaller variant of one of the most powerful models.",
+            id: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+        },
         {
             description: "Very powerful text generation model trained to follow instructions.",
             id: "meta-llama/Meta-Llama-3.1-8B-Instruct",
@@ -69,13 +76,17 @@ const taskData = {
             id: "PowerInfer/SmallThinker-3B-Preview",
         },
         {
-            description: "Strong text generation model to follow instructions.",
-            id: "Qwen/Qwen2.5-7B-Instruct",
+            description: "Strong conversational model that supports very long instructions.",
+            id: "Qwen/Qwen2.5-7B-Instruct-1M",
         },
         {
             description: "Text generation model used to write code.",
             id: "Qwen/Qwen2.5-Coder-32B-Instruct",
         },
+        {
+            description: "Powerful reasoning based open large language model.",
+            id: "deepseek-ai/DeepSeek-R1",
+        },
     ],
     spaces: [
         {

package/dist/esm/tasks/text-to-image/inference.d.ts

@@ -26,6 +26,10 @@ export interface TextToImageParameters {
      * the text prompt, but values too high may cause saturation and other artifacts.
      */
     guidance_scale?: number;
+    /**
+     * The height in pixels of the output image
+     */
+    height?: number;
     /**
      * One prompt to guide what NOT to include in image generation.
      */
@@ -44,17 +48,9 @@ export interface TextToImageParameters {
      */
     seed?: number;
     /**
-     * The size in pixel of the output image
+     * The width in pixels of the output image
      */
-    target_size?: TargetSize;
-    [property: string]: unknown;
-}
-/**
- * The size in pixel of the output image
- */
-export interface TargetSize {
-    height: number;
-    width: number;
+    width?: number;
     [property: string]: unknown;
 }
 /**

package/dist/esm/tasks/text-to-image/inference.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,WAAW,CAAC,EAAE,UAAU,CAAC;IACzB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,MAAM,CAAC;IACd,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/text-to-image/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;OAEG;IACH,UAAU,CAAC,EAAE,qBAAqB,CAAC;IACnC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IACd;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.15.6",
+  "version": "0.15.7",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/hardware.ts

@@ -1,6 +1,6 @@
 /**
- * Biden AI Executive Order
- * https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
+ * Biden AI Executive Order (since revoked by President Trump):
+ * https://web.archive.org/web/20250105222429/https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
  */
 export const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL = 10 ** 14;
 export const TFLOPS_THRESHOLD_WHITE_HOUSE_MODEL_TRAINING_TOTAL_BIOLOGY = 10 ** 11;

package/src/library-to-tasks.ts

@@ -43,7 +43,7 @@ export const LIBRARY_TASK_MAPPING: Partial<Record<ModelLibraryKey, PipelineType[
 		"text2text-generation",
 	],
 	stanza: ["token-classification"],
-	timm: ["image-classification"],
+	timm: ["image-classification", "image-feature-extraction"],
 	transformers: [
 		"audio-classification",
 		"automatic-speech-recognition",
@@ -52,6 +52,7 @@ export const LIBRARY_TASK_MAPPING: Partial<Record<ModelLibraryKey, PipelineType[
 		"feature-extraction",
 		"fill-mask",
 		"image-classification",
+		"image-feature-extraction",
 		"image-segmentation",
 		"image-to-image",
 		"image-to-text",

package/src/model-libraries-snippets.ts

@@ -1186,7 +1186,7 @@ model = BiRefNet.from_pretrained("${model.id}")`,
 export const swarmformer = (model: ModelData): string[] => [
 	`from swarmformer import SwarmFormerModel
 
-model = SwarmFormerModel.from_pretrained("${model.id}", trust_remote_code=True)
+model = SwarmFormerModel.from_pretrained("${model.id}")
 `,
 ];
 

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

@@ -145,6 +145,6 @@ export interface AutomaticSpeechRecognitionOutputChunk {
 	/**
 	 * The start and end timestamps corresponding with the text
 	 */
-	timestamps: number[];
+	timestamp: number[];
 	[property: string]: unknown;
 }

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

@@ -20,7 +20,7 @@
 						"type": "string",
 						"description": "A chunk of text identified by the model"
 					},
-					"timestamps": {
+					"timestamp": {
 						"type": "array",
 						"description": "The start and end timestamps corresponding with the text",
 						"items": {
@@ -30,7 +30,7 @@
 						"maxLength": 2
 					}
 				},
-				"required": ["text", "timestamps"]
+				"required": ["text", "timestamp"]
 			}
 		}
 	},

package/src/tasks/feature-extraction/inference.ts

@@ -13,9 +13,9 @@ export type FeatureExtractionOutput = Array<number[]>;
  */
 export interface FeatureExtractionInput {
 	/**
-	 * The text to embed.
+	 * The text or list of texts to embed.
 	 */
-	inputs: string;
+	inputs: FeatureExtractionInputs;
 	normalize?: boolean;
 	/**
 	 * The name of the prompt that should be used by for encoding. If not set, no prompt
@@ -34,4 +34,8 @@ export interface FeatureExtractionInput {
 	truncation_direction?: FeatureExtractionInputTruncationDirection;
 	[property: string]: unknown;
 }
+/**
+ * The text or list of texts to embed.
+ */
+export type FeatureExtractionInputs = string[] | string;
 export type FeatureExtractionInputTruncationDirection = "Left" | "Right";

package/src/tasks/feature-extraction/spec/input.json

@@ -7,8 +7,12 @@
 	"required": ["inputs"],
 	"properties": {
 		"inputs": {
-			"type": "string",
-			"description": "The text to embed."
+			"title": "FeatureExtractionInputs",
+			"oneOf": [
+				{ "type": "string" },
+				{ "type": "array", "items": { "type": "string" } }
+			],
+			"description": "The text or list of texts to embed."
 		},
 		"normalize": {
 			"type": "boolean",

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

@@ -60,7 +60,7 @@ const taskData: TaskDataCustom = {
 		},
 		{
 			description: "Strong image-text-to-text model.",
-			id: "Qwen/Qwen2-VL-7B-Instruct",
+			id: "Qwen/Qwen2.5-VL-7B-Instruct",
 		},
 		{
 			description: "Image-text-to-text model with reasoning capabilities.",
@@ -98,12 +98,12 @@ const taskData: TaskDataCustom = {
 		},
 		{
 			description: "An application that detects gaze.",
-			id: "smoondream/gaze-demo",
+			id: "moondream/gaze-demo",
 		},
 	],
 	summary:
 		"Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.",
-	widgetModels: ["meta-llama/Llama-3.2-11B-Vision-Instruct"],
+	widgetModels: ["Qwen/Qwen2-VL-7B-Instruct"],
 	youtubeId: "IoGaGfU1CIg",
 };
 

package/src/tasks/text-generation/data.ts

@@ -14,6 +14,10 @@ const taskData: TaskDataCustom = {
 			description: "Truly open-source, curated and cleaned dialogue dataset.",
 			id: "HuggingFaceH4/ultrachat_200k",
 		},
+		{
+			description: "A reasoning dataset.",
+			id: "open-r1/OpenThoughts-114k-math",
+		},
 		{
 			description: "A multilingual instruction dataset with preference ratings on responses.",
 			id: "allenai/tulu-3-sft-mixture",
@@ -57,10 +61,13 @@ const taskData: TaskDataCustom = {
 		},
 	],
 	models: [
-		{
-			description: "A text-generation model trained to follow instructions.",
+		{	description: "A text-generation model trained to follow instructions.",
 			id: "google/gemma-2-2b-it",
 		},
+		{
+			description: "Smaller variant of one of the most powerful models.",
+			id: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+		},
 		{
 			description: "Very powerful text generation model trained to follow instructions.",
 			id: "meta-llama/Meta-Llama-3.1-8B-Instruct",
@@ -74,13 +81,17 @@ const taskData: TaskDataCustom = {
 			id: "PowerInfer/SmallThinker-3B-Preview",
 		},
 		{
-			description: "Strong text generation model to follow instructions.",
-			id: "Qwen/Qwen2.5-7B-Instruct",
+			description: "Strong conversational model that supports very long instructions.",
+			id: "Qwen/Qwen2.5-7B-Instruct-1M",
 		},
 		{
 			description: "Text generation model used to write code.",
 			id: "Qwen/Qwen2.5-Coder-32B-Instruct",
 		},
+		{
+			description: "Powerful reasoning based open large language model.",
+			id: "deepseek-ai/DeepSeek-R1",
+		},
 	],
 	spaces: [
 		{

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

@@ -26,6 +26,10 @@ export interface TextToImageParameters {
 	 * the text prompt, but values too high may cause saturation and other artifacts.
 	 */
 	guidance_scale?: number;
+	/**
+	 * The height in pixels of the output image
+	 */
+	height?: number;
 	/**
 	 * One prompt to guide what NOT to include in image generation.
 	 */
@@ -44,17 +48,9 @@ export interface TextToImageParameters {
 	 */
 	seed?: number;
 	/**
-	 * The size in pixel of the output image
+	 * The width in pixels of the output image
 	 */
-	target_size?: TargetSize;
-	[property: string]: unknown;
-}
-/**
- * The size in pixel of the output image
- */
-export interface TargetSize {
-	height: number;
-	width: number;
+	width?: number;
 	[property: string]: unknown;
 }
 /**

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

@@ -31,18 +31,13 @@
 					"type": "integer",
 					"description": "The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference."
 				},
-				"target_size": {
-					"type": "object",
-					"description": "The size in pixel of the output image",
-					"properties": {
-						"width": {
-							"type": "integer"
-						},
-						"height": {
-							"type": "integer"
-						}
-					},
-					"required": ["width", "height"]
+				"width": {
+					"type": "integer",
+					"description": "The width in pixels of the output image"
+				},
+				"height": {
+					"type": "integer",
+					"description": "The height in pixels of the output image"
 				},
 				"scheduler": {
 					"type": "string",