@huggingface/tasks 0.19.7 → 0.19.9

package/dist/commonjs/tasks/index.js

@@ -18,36 +18,37 @@ const data_js_10 = __importDefault(require("./image-to-image/data.js"));
 const data_js_11 = __importDefault(require("./image-to-text/data.js"));
 const data_js_12 = __importDefault(require("./image-text-to-text/data.js"));
 const data_js_13 = __importDefault(require("./image-segmentation/data.js"));
-const data_js_14 = __importDefault(require("./mask-generation/data.js"));
-const data_js_15 = __importDefault(require("./object-detection/data.js"));
-const data_js_16 = __importDefault(require("./depth-estimation/data.js"));
-const data_js_17 = __importDefault(require("./placeholder/data.js"));
-const data_js_18 = __importDefault(require("./reinforcement-learning/data.js"));
-const data_js_19 = __importDefault(require("./question-answering/data.js"));
-const data_js_20 = __importDefault(require("./sentence-similarity/data.js"));
-const data_js_21 = __importDefault(require("./summarization/data.js"));
-const data_js_22 = __importDefault(require("./table-question-answering/data.js"));
-const data_js_23 = __importDefault(require("./tabular-classification/data.js"));
-const data_js_24 = __importDefault(require("./tabular-regression/data.js"));
-const data_js_25 = __importDefault(require("./text-to-image/data.js"));
-const data_js_26 = __importDefault(require("./text-to-speech/data.js"));
-const data_js_27 = __importDefault(require("./token-classification/data.js"));
-const data_js_28 = __importDefault(require("./translation/data.js"));
-const data_js_29 = __importDefault(require("./text-classification/data.js"));
-const data_js_30 = __importDefault(require("./text-generation/data.js"));
-const data_js_31 = __importDefault(require("./text-ranking/data.js"));
-const data_js_32 = __importDefault(require("./text-to-video/data.js"));
-const data_js_33 = __importDefault(require("./unconditional-image-generation/data.js"));
-const data_js_34 = __importDefault(require("./video-classification/data.js"));
-const data_js_35 = __importDefault(require("./visual-document-retrieval/data.js"));
-const data_js_36 = __importDefault(require("./visual-question-answering/data.js"));
-const data_js_37 = __importDefault(require("./zero-shot-classification/data.js"));
-const data_js_38 = __importDefault(require("./zero-shot-image-classification/data.js"));
-const data_js_39 = __importDefault(require("./zero-shot-object-detection/data.js"));
-const data_js_40 = __importDefault(require("./image-to-3d/data.js"));
-const data_js_41 = __importDefault(require("./text-to-3d/data.js"));
-const data_js_42 = __importDefault(require("./keypoint-detection/data.js"));
-const data_js_43 = __importDefault(require("./video-text-to-text/data.js"));
+const data_js_14 = __importDefault(require("./image-to-video/data.js"));
+const data_js_15 = __importDefault(require("./mask-generation/data.js"));
+const data_js_16 = __importDefault(require("./object-detection/data.js"));
+const data_js_17 = __importDefault(require("./depth-estimation/data.js"));
+const data_js_18 = __importDefault(require("./placeholder/data.js"));
+const data_js_19 = __importDefault(require("./reinforcement-learning/data.js"));
+const data_js_20 = __importDefault(require("./question-answering/data.js"));
+const data_js_21 = __importDefault(require("./sentence-similarity/data.js"));
+const data_js_22 = __importDefault(require("./summarization/data.js"));
+const data_js_23 = __importDefault(require("./table-question-answering/data.js"));
+const data_js_24 = __importDefault(require("./tabular-classification/data.js"));
+const data_js_25 = __importDefault(require("./tabular-regression/data.js"));
+const data_js_26 = __importDefault(require("./text-to-image/data.js"));
+const data_js_27 = __importDefault(require("./text-to-speech/data.js"));
+const data_js_28 = __importDefault(require("./token-classification/data.js"));
+const data_js_29 = __importDefault(require("./translation/data.js"));
+const data_js_30 = __importDefault(require("./text-classification/data.js"));
+const data_js_31 = __importDefault(require("./text-generation/data.js"));
+const data_js_32 = __importDefault(require("./text-ranking/data.js"));
+const data_js_33 = __importDefault(require("./text-to-video/data.js"));
+const data_js_34 = __importDefault(require("./unconditional-image-generation/data.js"));
+const data_js_35 = __importDefault(require("./video-classification/data.js"));
+const data_js_36 = __importDefault(require("./visual-document-retrieval/data.js"));
+const data_js_37 = __importDefault(require("./visual-question-answering/data.js"));
+const data_js_38 = __importDefault(require("./zero-shot-classification/data.js"));
+const data_js_39 = __importDefault(require("./zero-shot-image-classification/data.js"));
+const data_js_40 = __importDefault(require("./zero-shot-object-detection/data.js"));
+const data_js_41 = __importDefault(require("./image-to-3d/data.js"));
+const data_js_42 = __importDefault(require("./text-to-3d/data.js"));
+const data_js_43 = __importDefault(require("./keypoint-detection/data.js"));
+const data_js_44 = __importDefault(require("./video-text-to-text/data.js"));
 /**
  * Model libraries compatible with each ML task
  */
@@ -121,7 +122,7 @@ exports.TASKS_MODEL_LIBRARIES = {
  * If the partialTaskData argument is left undefined,
  * the default placeholder data will be used.
  */
-function getData(type, partialTaskData = data_js_17.default) {
+function getData(type, partialTaskData = data_js_18.default) {
     return {
         ...partialTaskData,
         id: type,
@@ -137,11 +138,11 @@ exports.TASKS_DATA = {
     "any-to-any": getData("any-to-any", data_js_1.default),
     "audio-classification": getData("audio-classification", data_js_2.default),
     "audio-to-audio": getData("audio-to-audio", data_js_3.default),
-    "audio-text-to-text": getData("audio-text-to-text", data_js_17.default),
+    "audio-text-to-text": getData("audio-text-to-text", data_js_18.default),
     "automatic-speech-recognition": getData("automatic-speech-recognition", data_js_4.default),
-    "depth-estimation": getData("depth-estimation", data_js_16.default),
+    "depth-estimation": getData("depth-estimation", data_js_17.default),
     "document-question-answering": getData("document-question-answering", data_js_5.default),
-    "visual-document-retrieval": getData("visual-document-retrieval", data_js_35.default),
+    "visual-document-retrieval": getData("visual-document-retrieval", data_js_36.default),
     "feature-extraction": getData("feature-extraction", data_js_6.default),
     "fill-mask": getData("fill-mask", data_js_7.default),
     "graph-ml": undefined,
@@ -151,42 +152,42 @@ exports.TASKS_DATA = {
     "image-to-image": getData("image-to-image", data_js_10.default),
     "image-text-to-text": getData("image-text-to-text", data_js_12.default),
     "image-to-text": getData("image-to-text", data_js_11.default),
-    "image-to-video": undefined,
-    "keypoint-detection": getData("keypoint-detection", data_js_42.default),
-    "mask-generation": getData("mask-generation", data_js_14.default),
+    "image-to-video": getData("image-to-video", data_js_14.default),
+    "keypoint-detection": getData("keypoint-detection", data_js_43.default),
+    "mask-generation": getData("mask-generation", data_js_15.default),
     "multiple-choice": undefined,
-    "object-detection": getData("object-detection", data_js_15.default),
-    "video-classification": getData("video-classification", data_js_34.default),
+    "object-detection": getData("object-detection", data_js_16.default),
+    "video-classification": getData("video-classification", data_js_35.default),
     other: undefined,
-    "question-answering": getData("question-answering", data_js_19.default),
-    "reinforcement-learning": getData("reinforcement-learning", data_js_18.default),
+    "question-answering": getData("question-answering", data_js_20.default),
+    "reinforcement-learning": getData("reinforcement-learning", data_js_19.default),
     robotics: undefined,
-    "sentence-similarity": getData("sentence-similarity", data_js_20.default),
-    summarization: getData("summarization", data_js_21.default),
-    "table-question-answering": getData("table-question-answering", data_js_22.default),
+    "sentence-similarity": getData("sentence-similarity", data_js_21.default),
+    summarization: getData("summarization", data_js_22.default),
+    "table-question-answering": getData("table-question-answering", data_js_23.default),
     "table-to-text": undefined,
-    "tabular-classification": getData("tabular-classification", data_js_23.default),
-    "tabular-regression": getData("tabular-regression", data_js_24.default),
+    "tabular-classification": getData("tabular-classification", data_js_24.default),
+    "tabular-regression": getData("tabular-regression", data_js_25.default),
     "tabular-to-text": undefined,
-    "text-classification": getData("text-classification", data_js_29.default),
-    "text-generation": getData("text-generation", data_js_30.default),
-    "text-ranking": getData("text-ranking", data_js_31.default),
+    "text-classification": getData("text-classification", data_js_30.default),
+    "text-generation": getData("text-generation", data_js_31.default),
+    "text-ranking": getData("text-ranking", data_js_32.default),
     "text-retrieval": undefined,
-    "text-to-image": getData("text-to-image", data_js_25.default),
-    "text-to-speech": getData("text-to-speech", data_js_26.default),
+    "text-to-image": getData("text-to-image", data_js_26.default),
+    "text-to-speech": getData("text-to-speech", data_js_27.default),
     "text-to-audio": undefined,
-    "text-to-video": getData("text-to-video", data_js_32.default),
+    "text-to-video": getData("text-to-video", data_js_33.default),
     "text2text-generation": undefined,
     "time-series-forecasting": undefined,
-    "token-classification": getData("token-classification", data_js_27.default),
-    translation: getData("translation", data_js_28.default),
-    "unconditional-image-generation": getData("unconditional-image-generation", data_js_33.default),
-    "video-text-to-text": getData("video-text-to-text", data_js_43.default),
-    "visual-question-answering": getData("visual-question-answering", data_js_36.default),
+    "token-classification": getData("token-classification", data_js_28.default),
+    translation: getData("translation", data_js_29.default),
+    "unconditional-image-generation": getData("unconditional-image-generation", data_js_34.default),
+    "video-text-to-text": getData("video-text-to-text", data_js_44.default),
+    "visual-question-answering": getData("visual-question-answering", data_js_37.default),
     "voice-activity-detection": undefined,
-    "zero-shot-classification": getData("zero-shot-classification", data_js_37.default),
-    "zero-shot-image-classification": getData("zero-shot-image-classification", data_js_38.default),
-    "zero-shot-object-detection": getData("zero-shot-object-detection", data_js_39.default),
-    "text-to-3d": getData("text-to-3d", data_js_41.default),
-    "image-to-3d": getData("image-to-3d", data_js_40.default),
+    "zero-shot-classification": getData("zero-shot-classification", data_js_38.default),
+    "zero-shot-image-classification": getData("zero-shot-image-classification", data_js_39.default),
+    "zero-shot-object-detection": getData("zero-shot-object-detection", data_js_40.default),
+    "text-to-3d": getData("text-to-3d", data_js_42.default),
+    "image-to-3d": getData("image-to-3d", data_js_41.default),
 };

package/dist/esm/hardware.d.ts

@@ -96,6 +96,10 @@ export declare const SKUS: {
                 tflops: number;
                 memory: number[];
             };
+            "RTX A5000": {
+                tflops: number;
+                memory: number[];
+            };
             "RTX A4000": {
                 tflops: number;
                 memory: number[];
@@ -529,6 +533,9 @@ export declare const SKUS: {
             "Intel Core Ultra 7 265KF": {
                 tflops: number;
             };
+            "Intel Core 14th Generation (i7)": {
+                tflops: number;
+            };
             "Intel Core 13th Generation (i9)": {
                 tflops: number;
             };

package/dist/esm/hardware.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"hardware.d.ts","sourceRoot":"","sources":["../../src/hardware.ts"],"names":[],"mappings":"AAAA;;;GAGG;AACH,eAAO,MAAM,iDAAiD,QAAW,CAAC;AAC1E,eAAO,MAAM,yDAAyD,QAAW,CAAC;AAClF,eAAO,MAAM,oCAAoC,QAAU,CAAC;AAE5D;;;GAGG;AACH,eAAO,MAAM,+CAA+C,QAAW,CAAC;AAExE,MAAM,WAAW,YAAY;IAC5B;;;;;;;;;OASG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;CAClB;AAED,eAAO,MAAM,sBAAsB,UAAqD,CAAC;AAEzF,eAAO,MAAM,IAAI;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAiqBuD,CAAC;AAEzE,MAAM,MAAM,OAAO,GAAG,MAAM,OAAO,IAAI,CAAC"}
+{"version":3,"file":"hardware.d.ts","sourceRoot":"","sources":["../../src/hardware.ts"],"names":[],"mappings":"AAAA;;;GAGG;AACH,eAAO,MAAM,iDAAiD,QAAW,CAAC;AAC1E,eAAO,MAAM,yDAAyD,QAAW,CAAC;AAClF,eAAO,MAAM,oCAAoC,QAAU,CAAC;AAE5D;;;GAGG;AACH,eAAO,MAAM,+CAA+C,QAAW,CAAC;AAExE,MAAM,WAAW,YAAY;IAC5B;;;;;;;;;OASG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;;OAGG;IACH,MAAM,CAAC,EAAE,MAAM,EAAE,CAAC;CAClB;AAED,eAAO,MAAM,sBAAsB,UAAqD,CAAC;AAEzF,eAAO,MAAM,IAAI;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAwqBuD,CAAC;AAEzE,MAAM,MAAM,OAAO,GAAG,MAAM,OAAO,IAAI,CAAC"}

package/dist/esm/hardware.js

@@ -78,6 +78,10 @@ export const SKUS = {
                 tflops: 38.7,
                 memory: [48],
             },
+            "RTX A5000": {
+                tflops: 34.1,
+                memory: [24],
+            },
             "RTX A4000": {
                 tflops: 19.2,
                 memory: [16],
@@ -511,6 +515,9 @@ export const SKUS = {
             "Intel Core Ultra 7 265KF": {
                 tflops: 1.53,
             },
+            "Intel Core 14th Generation (i7)": {
+                tflops: 0.8,
+            },
             "Intel Core 13th Generation (i9)": {
                 tflops: 0.85,
             },

package/dist/esm/local-apps.js

@@ -36,18 +36,18 @@ function getQuantTag(filepath) {
 const snippetLlamacpp = (model, filepath) => {
     const command = (binary) => {
         const snippet = ["# Load and run the model:", `${binary} -hf ${model.id}${getQuantTag(filepath)}`];
-        if (!model.tags.includes("conversational")) {
-            // for non-conversational models, add a prompt
-            snippet[snippet.length - 1] += " \\";
-            snippet.push('  -p "Once upon a time,"');
-        }
         return snippet.join("\n");
     };
     return [
         {
             title: "Install from brew",
             setup: "brew install llama.cpp",
-            content: command("llama-cli"),
+            content: command("llama-server"),
+        },
+        {
+            title: "Install from WinGet (Windows)",
+            setup: "winget install llama.cpp",
+            content: command("llama-server"),
         },
         {
             title: "Use pre-built binary",
@@ -56,17 +56,17 @@ const snippetLlamacpp = (model, filepath) => {
                 "# Download pre-built binary from:",
                 "# https://github.com/ggerganov/llama.cpp/releases",
             ].join("\n"),
-            content: command("./llama-cli"),
+            content: command("./llama-server"),
         },
         {
             title: "Build from source code",
             setup: [
                 "git clone https://github.com/ggerganov/llama.cpp.git",
                 "cd llama.cpp",
-                "cmake -B build -DLLAMA_CURL=ON",
-                "cmake --build build -j --target llama-cli",
+                "cmake -B build",
+                "cmake --build build -j --target llama-server",
             ].join("\n"),
-            content: command("./build/bin/llama-cli"),
+            content: command("./build/bin/llama-server"),
         },
     ];
 };

package/dist/esm/local-apps.spec.js

@@ -10,7 +10,7 @@ describe("local-apps", () => {
         };
         const snippet = snippetFunc(model);
         expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
+llama-server -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
     });
     it("llama.cpp non-conversational", async () => {
         const { snippet: snippetFunc } = LOCAL_APPS["llama.cpp"];
@@ -21,8 +21,7 @@ llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF:{{QUANT_TAG}}`);
         };
         const snippet = snippetFunc(model);
         expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli -hf mlabonne/gemma-2b-GGUF:{{QUANT_TAG}} \\
-  -p "Once upon a time,"`);
+llama-server -hf mlabonne/gemma-2b-GGUF:{{QUANT_TAG}}`);
     });
     it("vLLM conversational llm", async () => {
         const { snippet: snippetFunc } = LOCAL_APPS["vllm"];

package/dist/esm/model-libraries.d.ts

@@ -112,6 +112,13 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         countDownloads: string;
         snippets: (model: ModelData) => string[];
     };
+    "bagel-mot": {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        filter: false;
+        countDownloads: string;
+    };
     ben2: {
         prettyLabel: string;
         repoName: string;
@@ -931,6 +938,14 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         filter: true;
         countDownloads: string;
     };
+    torchgeo: {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        docsUrl: string;
+        filter: false;
+        countDownloads: string;
+    };
     transformers: {
         prettyLabel: string;
         repoName: string;
@@ -1040,5 +1055,5 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
 };
 export type ModelLibraryKey = keyof typeof MODEL_LIBRARIES_UI_ELEMENTS;
 export declare const ALL_MODEL_LIBRARY_KEYS: ModelLibraryKey[];
-export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "anemoi" | "araclip" | "asteroid" | "audiocraft" | "audioseal" | "ben2" | "bertopic" | "big_vision" | "birder" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "comet" | "cosmos" | "cxr-foundation" | "deepforest" | "depth-anything-v2" | "depth-pro" | "derm-foundation" | "describe-anything" | "dia-tts" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "clipscope" | "cosyvoice" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "geometry-crafter" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "htrflow" | "hunyuan-dit" | "hunyuan3d-2" | "imstoucan" | "index-tts" | "infinite-you" | "keras" | "tf-keras" | "keras-hub" | "kimi-audio" | "k2" | "lightning-ir" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "matanyone" | "mesh-anything" | "merlin" | "medvae" | "mitie" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open-oasis" | "open_clip" | "open-sora" | "outetts" | "paddlenlp" | "peft" | "perception-encoder" | "phantom-wan" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "swarmformer" | "f5-tts" | "genmo" | "tensorflowtts" | "tabpfn" | "terratorch" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "trellis" | "ultralytics" | "uni-3dar" | "unity-sentis" | "sana" | "vfi-mamba" | "voicecraft" | "wham" | "whisperkit" | "yolov10" | "zonos" | "3dtopia-xl")[];
+export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "anemoi" | "araclip" | "asteroid" | "audiocraft" | "audioseal" | "bagel-mot" | "ben2" | "bertopic" | "big_vision" | "birder" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "comet" | "cosmos" | "cxr-foundation" | "deepforest" | "depth-anything-v2" | "depth-pro" | "derm-foundation" | "describe-anything" | "dia-tts" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "clipscope" | "cosyvoice" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "geometry-crafter" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "htrflow" | "hunyuan-dit" | "hunyuan3d-2" | "imstoucan" | "index-tts" | "infinite-you" | "keras" | "tf-keras" | "keras-hub" | "kimi-audio" | "k2" | "lightning-ir" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "matanyone" | "mesh-anything" | "merlin" | "medvae" | "mitie" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open-oasis" | "open_clip" | "open-sora" | "outetts" | "paddlenlp" | "peft" | "perception-encoder" | "phantom-wan" | "pxia" | "pyannote-audio" | "py-feat" | "pythae" | "recurrentgemma" | "relik" | "refiners" | "reverb" | "saelens" | "sam2" | "sample-factory" | "sapiens" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "ssr-speech" | "stable-audio-tools" | "diffusion-single-file" | "seed-story" | "soloaudio" | "stable-baselines3" | "stanza" | "swarmformer" | "f5-tts" | "genmo" | "tensorflowtts" | "tabpfn" | "terratorch" | "tic-clip" | "timesfm" | "timm" | "torchgeo" | "transformers" | "transformers.js" | "trellis" | "ultralytics" | "uni-3dar" | "unity-sentis" | "sana" | "vfi-mamba" | "voicecraft" | "wham" | "whisperkit" | "yolov10" | "zonos" | "3dtopia-xl")[];
 //# sourceMappingURL=model-libraries.d.ts.map

package/dist/esm/model-libraries.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,gCAAgC,CAAC;AAEzE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;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;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA89BI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,EAA+C,eAAe,EAAE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,o0DAQ1B,CAAC"}
+{"version":3,"file":"model-libraries.d.ts","sourceRoot":"","sources":["../../src/model-libraries.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,gCAAgC,CAAC;AAEzE;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC;;;;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;IACjB;;OAEG;IACH,QAAQ,CAAC,EAAE,CAAC,KAAK,EAAE,SAAS,KAAK,MAAM,EAAE,CAAC;IAC1C;;;;;OAKG;IACH,cAAc,CAAC,EAAE,kBAAkB,CAAC;IACpC;;;OAGG;IACH,MAAM,CAAC,EAAE,OAAO,CAAC;CACjB;AAED;;;;;;;;;;;;;GAaG;AAEH,eAAO,MAAM,2BAA2B;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA6+BI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,EAA+C,eAAe,EAAE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,+1DAQ1B,CAAC"}

package/dist/esm/model-libraries.js

@@ -72,6 +72,13 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         countDownloads: `path_extension:"pth"`,
         snippets: snippets.audioseal,
     },
+    "bagel-mot": {
+        prettyLabel: "Bagel",
+        repoName: "Bagel",
+        repoUrl: "https://github.com/ByteDance-Seed/Bagel/",
+        filter: false,
+        countDownloads: `path:"llm_config.json"`,
+    },
     ben2: {
         prettyLabel: "BEN2",
         repoName: "BEN2",
@@ -885,7 +892,7 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         repoName: "timesfm",
         repoUrl: "https://github.com/google-research/timesfm",
         filter: false,
-        countDownloads: `path:"checkpoints/checkpoint_1100000/state/checkpoint"`,
+        countDownloads: `path:"checkpoints/checkpoint_1100000/state/checkpoint" OR path:"checkpoints/checkpoint_2150000/state/checkpoint" OR path_extension:"ckpt"`,
     },
     timm: {
         prettyLabel: "timm",
@@ -896,6 +903,14 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         filter: true,
         countDownloads: `path:"pytorch_model.bin" OR path:"model.safetensors"`,
     },
+    torchgeo: {
+        prettyLabel: "TorchGeo",
+        repoName: "TorchGeo",
+        repoUrl: "https://github.com/microsoft/torchgeo",
+        docsUrl: "https://torchgeo.readthedocs.io/",
+        filter: false,
+        countDownloads: `path_extension:"pt" OR path_extension:"pth"`,
+    },
     transformers: {
         prettyLabel: "Transformers",
         repoName: "🤗/transformers",

package/dist/esm/snippets/inputs.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"inputs.d.ts","sourceRoot":"","sources":["../../../src/snippets/inputs.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,0BAA0B,EAAE,MAAM,mBAAmB,CAAC;AACpE,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AAsJnD,wBAAgB,oBAAoB,CACnC,KAAK,EAAE,gBAAgB,EACvB,MAAM,UAAQ,EACd,QAAQ,UAAQ,GACd,MAAM,GAAG,0BAA0B,EAAE,CAmBvC"}
+{"version":3,"file":"inputs.d.ts","sourceRoot":"","sources":["../../../src/snippets/inputs.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,0BAA0B,EAAE,MAAM,mBAAmB,CAAC;AACpE,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,YAAY,CAAC;AA4JnD,wBAAgB,oBAAoB,CACnC,KAAK,EAAE,gBAAgB,EACvB,MAAM,UAAQ,EACd,QAAQ,UAAQ,GACd,MAAM,GAAG,0BAA0B,EAAE,CAmBvC"}

package/dist/esm/snippets/inputs.js

@@ -65,6 +65,10 @@ const inputsImageToImage = () => `{
     "image": "cat.png",
     "prompt": "Turn the cat into a tiger."
 }`;
+const inputsImageToVideo = () => `{
+    "image": "cat.png",
+    "prompt": "The cat starts to dance"
+}`;
 const inputsImageSegmentation = () => `"cats.jpg"`;
 const inputsObjectDetection = () => `"cats.jpg"`;
 const inputsAudioToAudio = () => `"sample1.flac"`;
@@ -86,6 +90,7 @@ const modelInputSnippets = {
     "image-classification": inputsImageClassification,
     "image-to-text": inputsImageToText,
     "image-to-image": inputsImageToImage,
+    "image-to-video": inputsImageToVideo,
     "image-segmentation": inputsImageSegmentation,
     "object-detection": inputsObjectDetection,
     "question-answering": inputsQuestionAnswering,

package/dist/esm/tasks/image-to-video/data.d.ts

@@ -0,0 +1,4 @@
+import type { TaskDataCustom } from "../index.js";
+declare const taskData: TaskDataCustom;
+export default taskData;
+//# sourceMappingURL=data.d.ts.map

package/dist/esm/tasks/image-to-video/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-to-video/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAyHf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

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

@@ -0,0 +1,117 @@
+const taskData = {
+    datasets: [
+        {
+            description: "A benchmark dataset for reference image controlled video generation.",
+            id: "ali-vilab/VACE-Benchmark",
+        },
+        {
+            description: "A dataset of video generation style preferences.",
+            id: "Rapidata/sora-video-generation-style-likert-scoring",
+        },
+        {
+            description: "A dataset with videos and captions throughout the videos.",
+            id: "BestWishYsh/ChronoMagic",
+        },
+    ],
+    demo: {
+        inputs: [
+            {
+                filename: "image-to-video-input.jpg",
+                type: "img",
+            },
+            {
+                label: "Optional Text Prompt",
+                content: "This penguin is dancing",
+                type: "text",
+            },
+        ],
+        outputs: [
+            {
+                filename: "image-to-video-output.gif",
+                type: "img",
+            },
+        ],
+    },
+    metrics: [
+        {
+            description: "Fréchet Video Distance (FVD) measures the perceptual similarity between the distributions of generated videos and a set of real videos, assessing overall visual quality and temporal coherence of the video generated from an input image.",
+            id: "fvd",
+        },
+        {
+            description: "CLIP Score measures the semantic similarity between a textual prompt (if provided alongside the input image) and the generated video frames. It evaluates how well the video's generated content and motion align with the textual description, conditioned on the initial image.",
+            id: "clip_score",
+        },
+        {
+            description: "First Frame Fidelity, often measured using LPIPS (Learned Perceptual Image Patch Similarity), PSNR, or SSIM, quantifies how closely the first frame of the generated video matches the input conditioning image.",
+            id: "lpips",
+        },
+        {
+            description: "Identity Preservation Score measures the consistency of identity (e.g., a person's face or a specific object's characteristics) between the input image and throughout the generated video frames, often calculated using features from specialized models like face recognition (e.g., ArcFace) or re-identification models.",
+            id: "identity_preservation",
+        },
+        {
+            description: "Motion Score evaluates the quality, realism, and temporal consistency of motion in the video generated from a static image. This can be based on optical flow analysis (e.g., smoothness, magnitude), consistency of object trajectories, or specific motion plausibility assessments.",
+            id: "motion_score",
+        },
+    ],
+    models: [
+        {
+            description: "LTX-Video, a 13B parameter model for high quality video generation",
+            id: "Lightricks/LTX-Video-0.9.7-dev",
+        },
+        {
+            description: "A 14B parameter model for reference image controlled video generation",
+            id: "Wan-AI/Wan2.1-VACE-14B",
+        },
+        {
+            description: "An image-to-video generation model using FramePack F1 methodology with Hunyuan-DiT architecture",
+            id: "lllyasviel/FramePack_F1_I2V_HY_20250503",
+        },
+        {
+            description: "A distilled version of the LTX-Video-0.9.7-dev model for faster inference",
+            id: "Lightricks/LTX-Video-0.9.7-distilled",
+        },
+        {
+            description: "An image-to-video generation model by Skywork AI, 14B parameters, producing 720p videos.",
+            id: "Skywork/SkyReels-V2-I2V-14B-720P",
+        },
+        {
+            description: "Image-to-video variant of Tencent's HunyuanVideo.",
+            id: "tencent/HunyuanVideo-I2V",
+        },
+        {
+            description: "A 14B parameter model for 720p image-to-video generation by Wan-AI.",
+            id: "Wan-AI/Wan2.1-I2V-14B-720P",
+        },
+        {
+            description: "A Diffusers version of the Wan2.1-I2V-14B-720P model for 720p image-to-video generation.",
+            id: "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers",
+        },
+    ],
+    spaces: [
+        {
+            description: "An application to generate videos fast.",
+            id: "Lightricks/ltx-video-distilled",
+        },
+        {
+            description: "Generate videos with the FramePack-F1",
+            id: "linoyts/FramePack-F1",
+        },
+        {
+            description: "Generate videos with the FramePack",
+            id: "lisonallen/framepack-i2v",
+        },
+        {
+            description: "Wan2.1 with CausVid LoRA",
+            id: "multimodalart/wan2-1-fast",
+        },
+        {
+            description: "A demo for Stable Video Diffusion",
+            id: "multimodalart/stable-video-diffusion",
+        },
+    ],
+    summary: "Image-to-video models take a still image as input and generate a video. These models can be guided by text prompts to influence the content and style of the output video.",
+    widgetModels: [],
+    youtubeId: undefined,
+};
+export default taskData;

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

@@ -0,0 +1,75 @@
+/**
+ * Inference code generated from the JSON schema spec in ./spec
+ *
+ * Using src/scripts/inference-codegen
+ */
+/**
+ * Inputs for Image To Video inference
+ */
+export interface ImageToVideoInput {
+    /**
+     * 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: Blob;
+    /**
+     * Additional inference parameters for Image To Video
+     */
+    parameters?: ImageToVideoParameters;
+    [property: string]: unknown;
+}
+/**
+ * Additional inference parameters for Image To Video
+ */
+export interface ImageToVideoParameters {
+    /**
+     * For diffusion models. A higher guidance scale value encourages the model to generate
+     * videos closely linked to the text prompt at the expense of lower image quality.
+     */
+    guidance_scale?: number;
+    /**
+     * One prompt to guide what NOT to include in video generation.
+     */
+    negative_prompt?: string;
+    /**
+     * The num_frames parameter determines how many video frames are generated.
+     */
+    num_frames?: number;
+    /**
+     * The number of denoising steps. More denoising steps usually lead to a higher quality
+     * video at the expense of slower inference.
+     */
+    num_inference_steps?: number;
+    /**
+     * The text prompt to guide the video generation.
+     */
+    prompt?: string;
+    /**
+     * Seed for the random number generator.
+     */
+    seed?: number;
+    /**
+     * The size in pixel of the output video frames.
+     */
+    target_size?: TargetSize;
+    [property: string]: unknown;
+}
+/**
+ * The size in pixel of the output video frames.
+ */
+export interface TargetSize {
+    height: number;
+    width: number;
+    [property: string]: unknown;
+}
+/**
+ * Outputs of inference for the Image To Video task
+ */
+export interface ImageToVideoOutput {
+    /**
+     * The generated video returned as raw bytes in the payload.
+     */
+    video: unknown;
+    [property: string]: unknown;
+}
+//# sourceMappingURL=inference.d.ts.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"inference.d.ts","sourceRoot":"","sources":["../../../../src/tasks/image-to-video/inference.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AACH;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;;OAGG;IACH,MAAM,EAAE,IAAI,CAAC;IACb;;OAEG;IACH,UAAU,CAAC,EAAE,sBAAsB,CAAC;IACpC,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B;AACD;;GAEG;AACH,MAAM,WAAW,sBAAsB;IACtC;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;;OAGG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAC;IAC7B;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;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,kBAAkB;IAClC;;OAEG;IACH,KAAK,EAAE,OAAO,CAAC;IACf,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC;CAC5B"}

package/dist/esm/tasks/image-to-video/inference.js

@@ -0,0 +1 @@
+export {};

package/dist/esm/tasks/index.d.ts

@@ -9,6 +9,7 @@ export type { ImageClassificationInput, ImageClassificationOutput, ImageClassifi
 export type * from "./image-to-image/inference.js";
 export type { ImageToTextInput, ImageToTextOutput, ImageToTextParameters } from "./image-to-text/inference.js";
 export type * from "./image-segmentation/inference.js";
+export type { ImageToVideoInput, ImageToVideoOutput, ImageToVideoParameters } from "./image-to-video/inference.js";
 export type * from "./object-detection/inference.js";
 export type * from "./depth-estimation/inference.js";
 export type * from "./question-answering/inference.js";