@huggingface/tasks 0.13.15 → 0.13.17

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

@@ -172,6 +172,7 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         prettyLabel: string;
         repoName: string;
         repoUrl: string;
+        snippets: (model: ModelData) => string[];
         filter: false;
         countDownloads: string;
     };
@@ -202,6 +203,7 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         prettyLabel: string;
         repoName: string;
         repoUrl: string;
+        snippets: (model: ModelData) => string[];
         filter: false;
         countDownloads: string;
     };
@@ -398,13 +400,6 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         snippets: (model: ModelData) => string[];
         countDownloads: string;
     };
-    "keras-nlp": {
-        prettyLabel: string;
-        repoName: string;
-        repoUrl: string;
-        docsUrl: string;
-        snippets: (model: ModelData) => string[];
-    };
     "keras-hub": {
         prettyLabel: string;
         repoName: string;
@@ -774,6 +769,15 @@ export declare const MODEL_LIBRARIES_UI_ELEMENTS: {
         repoName: string;
         repoUrl: string;
     };
+    terratorch: {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        docsUrl: string;
+        filter: false;
+        countDownloads: string;
+        snippets: (model: ModelData) => string[];
+    };
     "tic-clip": {
         prettyLabel: string;
         repoName: string;
@@ -884,5 +888,5 @@ 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" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birder" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "cosmos" | "cxr-foundation" | "deepforest" | "depth-anything-v2" | "depth-pro" | "derm-foundation" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "clipscope" | "cosyvoice" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "htrflow" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-nlp" | "keras-hub" | "k2" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "mitie" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open-oasis" | "open_clip" | "paddlenlp" | "peft" | "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" | "f5-tts" | "genmo" | "tensorflowtts" | "tabpfn" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "trellis" | "ultralytics" | "unity-sentis" | "sana" | "vfi-mamba" | "voicecraft" | "whisperkit" | "yolov10" | "3dtopia-xl")[];
+export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "anemoi" | "asteroid" | "audiocraft" | "audioseal" | "bertopic" | "big_vision" | "birder" | "birefnet" | "bm25s" | "champ" | "chat_tts" | "colpali" | "cosmos" | "cxr-foundation" | "deepforest" | "depth-anything-v2" | "depth-pro" | "derm-foundation" | "diffree" | "diffusers" | "diffusionkit" | "doctr" | "cartesia_pytorch" | "cartesia_mlx" | "clipscope" | "cosyvoice" | "cotracker" | "edsnlp" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gemma.cpp" | "gliner" | "glyph-byt5" | "grok" | "hallo" | "hezar" | "htrflow" | "hunyuan-dit" | "imstoucan" | "keras" | "tf-keras" | "keras-hub" | "k2" | "liveportrait" | "llama-cpp-python" | "mini-omni2" | "mindspore" | "mamba-ssm" | "mars5-tts" | "mesh-anything" | "mitie" | "ml-agents" | "mlx" | "mlx-image" | "mlc-llm" | "model2vec" | "moshi" | "nemo" | "open-oasis" | "open_clip" | "paddlenlp" | "peft" | "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" | "f5-tts" | "genmo" | "tensorflowtts" | "tabpfn" | "terratorch" | "tic-clip" | "timesfm" | "timm" | "transformers" | "transformers.js" | "trellis" | "ultralytics" | "unity-sentis" | "sana" | "vfi-mamba" | "voicecraft" | "whisperkit" | "yolov10" | "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;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA+zBI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,EAA+C,eAAe,EAAE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,ygDAQ1B,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;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAs0BI,CAAC;AAE7C,MAAM,MAAM,eAAe,GAAG,MAAM,OAAO,2BAA2B,CAAC;AAEvE,eAAO,MAAM,sBAAsB,EAA+C,eAAe,EAAE,CAAC;AAEpG,eAAO,MAAM,8BAA8B,0gDAQ1B,CAAC"}

package/dist/esm/model-libraries.js

@@ -132,6 +132,7 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         prettyLabel: "CXR Foundation",
         repoName: "cxr-foundation",
         repoUrl: "https://github.com/google-health/cxr-foundation",
+        snippets: snippets.cxr_foundation,
         filter: false,
         countDownloads: `path:"precomputed_embeddings/embeddings.npz" OR path:"pax-elixr-b-text/saved_model.pb"`,
     },
@@ -162,6 +163,7 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         prettyLabel: "Derm Foundation",
         repoName: "derm-foundation",
         repoUrl: "https://github.com/google-health/derm-foundation",
+        snippets: snippets.derm_foundation,
         filter: false,
         countDownloads: `path:"scin_dataset_precomputed_embeddings.npz" OR path:"saved_model.pb"`,
     },
@@ -360,13 +362,6 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         snippets: snippets.tf_keras,
         countDownloads: `path:"saved_model.pb"`,
     },
-    "keras-nlp": {
-        prettyLabel: "KerasNLP",
-        repoName: "KerasNLP",
-        repoUrl: "https://github.com/keras-team/keras-nlp",
-        docsUrl: "https://keras.io/keras_nlp/",
-        snippets: snippets.keras_nlp,
-    },
     "keras-hub": {
         prettyLabel: "KerasHub",
         repoName: "KerasHub",
@@ -500,7 +495,10 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         repoUrl: "https://github.com/mlfoundations/open_clip",
         snippets: snippets.open_clip,
         filter: true,
-        countDownloads: `path_extension:"bin" AND path_filename:*pytorch_model`,
+        countDownloads: `path:"open_clip_model.safetensors"
+			OR path:"model.safetensors"
+			OR path:"open_clip_pytorch_model.bin"
+			OR path:"pytorch_model.bin"`,
     },
     paddlenlp: {
         prettyLabel: "paddlenlp",
@@ -736,6 +734,15 @@ export const MODEL_LIBRARIES_UI_ELEMENTS = {
         repoName: "TabPFN",
         repoUrl: "https://github.com/PriorLabs/TabPFN",
     },
+    terratorch: {
+        prettyLabel: "TerraTorch",
+        repoName: "TerraTorch",
+        repoUrl: "https://github.com/IBM/terratorch",
+        docsUrl: "https://ibm.github.io/terratorch/",
+        filter: false,
+        countDownloads: `path_extension:"pt"`,
+        snippets: snippets.terratorch,
+    },
     "tic-clip": {
         prettyLabel: "TiC-CLIP",
         repoName: "TiC-CLIP",

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

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/audio-to-audio/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiEf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/audio-to-audio/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA6Df,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/audio-to-audio/data.js

@@ -34,10 +34,6 @@ const taskData = {
         },
     ],
     models: [
-        {
-            description: "A solid model of audio source separation.",
-            id: "speechbrain/sepformer-wham",
-        },
         {
             description: "A speech enhancement model.",
             id: "ResembleAI/resemble-enhance",

package/dist/esm/tasks/fill-mask/data.js

@@ -57,8 +57,8 @@ const taskData = {
     ],
     models: [
         {
-            description: "The famous BERT model.",
-            id: "google-bert/bert-base-uncased",
+            description: "State-of-the-art masked language model.",
+            id: "answerdotai/ModernBERT-large",
         },
         {
             description: "A multilingual model trained on 100 languages.",

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

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

package/dist/esm/tasks/image-classification/data.js

@@ -72,9 +72,8 @@ const taskData = {
     ],
     spaces: [
         {
-            // TO DO: write description
-            description: "An application that classifies what a given image is about.",
-            id: "nielsr/perceiver-image-classification",
+            description: "A leaderboard to evaluate different image classification models.",
+            id: "timm/leaderboard",
         },
     ],
     summary: "Image classification is the task of assigning a label or class to an entire image. Images are expected to have only one class for each image. Image classification models take an image as input and return a prediction about which class the image belongs to.",

package/dist/esm/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,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAsDf,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,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA2Df,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/image-feature-extraction/data.js

@@ -40,15 +40,20 @@ const taskData = {
             id: "facebook/dino-vitb16",
         },
         {
-            description: "Strong image feature extraction model made for information retrieval from documents.",
-            id: "vidore/colpali",
+            description: "Cutting-edge image feature extraction model.",
+            id: "apple/aimv2-large-patch14-336-distilled",
         },
         {
             description: "Strong image feature extraction model that can be used on images and documents.",
             id: "OpenGVLab/InternViT-6B-448px-V1-2",
         },
     ],
-    spaces: [],
+    spaces: [
+        {
+            description: "A leaderboard to evaluate different image-feature-extraction models on classification performances",
+            id: "timm/leaderboard",
+        },
+    ],
     summary: "Image feature extraction is the task of extracting features learnt in a computer vision model.",
     widgetModels: [],
 };

package/dist/esm/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,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiGf,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,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAyGf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

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

@@ -5,8 +5,8 @@ const taskData = {
             id: "liuhaotian/LLaVA-Instruct-150K",
         },
         {
-            description: "Conversation turns where questions involve image and text.",
-            id: "liuhaotian/LLaVA-Pretrain",
+            description: "Collection of image-text pairs on scientific topics.",
+            id: "DAMO-NLP-SG/multimodal_textbook",
         },
         {
             description: "A collection of datasets made for model fine-tuning.",
@@ -40,11 +40,15 @@ const taskData = {
     metrics: [],
     models: [
         {
-            description: "Powerful vision language model with great visual understanding and reasoning capabilities.",
-            id: "meta-llama/Llama-3.2-11B-Vision-Instruct",
+            description: "Small and efficient yet powerful vision language model.",
+            id: "HuggingFaceTB/SmolVLM-Instruct",
         },
         {
-            description: "Cutting-edge vision language models.",
+            description: "A screenshot understanding model used to control computers.",
+            id: "showlab/ShowUI-2B",
+        },
+        {
+            description: "Cutting-edge vision language model.",
             id: "allenai/Molmo-7B-D-0924",
         },
         {
@@ -56,8 +60,8 @@ const taskData = {
             id: "Qwen/Qwen2-VL-7B-Instruct",
         },
         {
-            description: "Strong image-text-to-text model.",
-            id: "mistralai/Pixtral-12B-2409",
+            description: "Image-text-to-text model with reasoning capabilities.",
+            id: "Qwen/QVQ-72B-Preview",
         },
         {
             description: "Strong image-text-to-text model focused on documents.",
@@ -81,14 +85,18 @@ const taskData = {
             description: "An image-text-to-text application focused on documents.",
             id: "stepfun-ai/GOT_official_online_demo",
         },
-        {
-            description: "An application to compare outputs of different vision language models.",
-            id: "merve/compare_VLMs",
-        },
         {
             description: "An application for chatting with an image-text-to-text model.",
             id: "GanymedeNil/Qwen2-VL-7B",
         },
+        {
+            description: "An application that parses screenshots into actions.",
+            id: "showlab/ShowUI",
+        },
+        {
+            description: "An application that detects gaze.",
+            id: "smoondream/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"],

package/dist/esm/tasks/image-to-3d/data.js

@@ -39,8 +39,8 @@ const taskData = {
             id: "hwjiang/Real3D",
         },
         {
-            description: "Generative 3D gaussian splatting model.",
-            id: "ashawkey/LGM",
+            description: "Consistent image-to-3d generation model.",
+            id: "stabilityai/stable-point-aware-3d",
         },
     ],
     spaces: [
@@ -53,8 +53,8 @@ const taskData = {
             id: "TencentARC/InstantMesh",
         },
         {
-            description: "Image-to-3D demo with mesh outputs.",
-            id: "stabilityai/TripoSR",
+            description: "Image-to-3D demo.",
+            id: "stabilityai/stable-point-aware-3d",
         },
         {
             description: "Image-to-3D demo with mesh outputs.",

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

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

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

@@ -8,6 +8,10 @@ const taskData = {
             description: "Multiple images of celebrities, used for facial expression translation",
             id: "huggan/CelebA-faces",
         },
+        {
+            description: "12M image-caption pairs.",
+            id: "Spawning/PD12M",
+        },
     ],
     demo: {
         inputs: [
@@ -48,16 +52,20 @@ const taskData = {
             id: "keras-io/super-resolution",
         },
         {
-            description: "A model that creates a set of variations of the input image in the style of DALL-E using Stable Diffusion.",
-            id: "lambdalabs/sd-image-variations-diffusers",
+            description: "A model for applying edits to images through image controls.",
+            id: "Yuanshi/OminiControl",
         },
         {
             description: "A model that generates images based on segments in the input image and the text prompt.",
             id: "mfidabel/controlnet-segment-anything",
         },
         {
-            description: "A model that takes an image and an instruction to edit the image.",
-            id: "timbrooks/instruct-pix2pix",
+            description: "Strong model for inpainting and outpainting.",
+            id: "black-forest-labs/FLUX.1-Fill-dev",
+        },
+        {
+            description: "Strong model for image editing using depth maps.",
+            id: "black-forest-labs/FLUX.1-Depth-dev-lora",
         },
     ],
     spaces: [

package/dist/esm/tasks/index.js

@@ -63,7 +63,7 @@ export const TASKS_MODEL_LIBRARIES = {
     "video-classification": ["transformers"],
     "mask-generation": ["transformers"],
     "multiple-choice": ["transformers"],
-    "object-detection": ["transformers", "transformers.js"],
+    "object-detection": ["transformers", "transformers.js", "ultralytics"],
     other: [],
     "question-answering": ["adapter-transformers", "allennlp", "transformers", "transformers.js"],
     robotics: [],

package/dist/esm/tasks/keypoint-detection/data.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/keypoint-detection/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cA6Cf,CAAC;AAEF,eAAe,QAAQ,CAAC"}
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/tasks/keypoint-detection/data.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAElD,QAAA,MAAM,QAAQ,EAAE,cAiDf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

package/dist/esm/tasks/keypoint-detection/data.js

@@ -29,6 +29,10 @@ const taskData = {
             description: "Strong keypoint detection model used to detect human pose.",
             id: "facebook/sapiens-pose-1b",
         },
+        {
+            description: "Powerful keypoint detection model used to detect human pose.",
+            id: "usyd-community/vitpose-plus-base",
+        },
     ],
     spaces: [
         {

package/dist/esm/tasks/object-detection/data.d.ts.map

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

package/dist/esm/tasks/object-detection/data.js

@@ -50,6 +50,10 @@ const taskData = {
             description: "Fast and accurate object detection model trained on COCO and Object365 datasets.",
             id: "PekingU/rtdetr_r18vd_coco_o365",
         },
+        {
+            description: "Object detection model for low-lying objects.",
+            id: "StephanST/WALDO30",
+        },
     ],
     spaces: [
         {
@@ -61,8 +65,8 @@ const taskData = {
             id: "Gradio-Blocks/Object-Detection-With-DETR-and-YOLOS",
         },
         {
-            description: "An application that shows multiple cutting edge techniques for object detection and tracking.",
-            id: "kadirnar/torchyolo",
+            description: "A cutting-edge object detection application.",
+            id: "Ultralytics/YOLO11",
         },
         {
             description: "An object tracking, segmentation and inpainting application.",

package/dist/esm/tasks/sentence-similarity/data.d.ts.map

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

package/dist/esm/tasks/sentence-similarity/data.js

@@ -64,9 +64,13 @@ const taskData = {
             id: "sentence-transformers/all-mpnet-base-v2",
         },
         {
-            description: "A multilingual robust sentence similarity model..",
+            description: "A multilingual robust sentence similarity model.",
             id: "BAAI/bge-m3",
         },
+        {
+            description: "A robust sentence similarity model.",
+            id: "HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5",
+        },
     ],
     spaces: [
         {

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,cA6Gf,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,cAgHf,CAAC;AAEF,eAAe,QAAQ,CAAC"}

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

@@ -1,24 +1,28 @@
 const taskData = {
     datasets: [
         {
-            description: "A large multilingual dataset of text crawled from the web.",
-            id: "mc4",
+            description: "Multilingual dataset used to evaluate text generation models.",
+            id: "CohereForAI/Global-MMLU",
         },
         {
-            description: "Diverse open-source data consisting of 22 smaller high-quality datasets. It was used to train GPT-Neo.",
-            id: "the_pile",
+            description: "High quality multilingual data used to train text-generation models.",
+            id: "HuggingFaceFW/fineweb-2",
         },
         {
             description: "Truly open-source, curated and cleaned dialogue dataset.",
             id: "HuggingFaceH4/ultrachat_200k",
         },
         {
-            description: "An instruction dataset with preference ratings on responses.",
-            id: "openbmb/UltraFeedback",
+            description: "A multilingual instruction dataset with preference ratings on responses.",
+            id: "allenai/tulu-3-sft-mixture",
         },
         {
             description: "A large synthetic dataset for alignment of text generation models.",
-            id: "argilla/magpie-ultra-v0.1",
+            id: "HuggingFaceTB/smoltalk",
+        },
+        {
+            description: "A dataset made for training text generation models solving math questions.",
+            id: "HuggingFaceTB/finemath",
         },
     ],
     demo: {
@@ -57,20 +61,20 @@ const taskData = {
             id: "meta-llama/Meta-Llama-3.1-8B-Instruct",
         },
         {
-            description: "Small yet powerful text generation model.",
-            id: "microsoft/Phi-3-mini-4k-instruct",
+            description: "Powerful text generation model by Microsoft.",
+            id: "microsoft/phi-4",
         },
         {
-            description: "A very powerful model that can solve mathematical problems.",
-            id: "AI-MO/NuminaMath-7B-TIR",
+            description: "A very powerful model with reasoning capabilities.",
+            id: "PowerInfer/SmallThinker-3B-Preview",
         },
         {
             description: "Strong text generation model to follow instructions.",
             id: "Qwen/Qwen2.5-7B-Instruct",
         },
         {
-            description: "Very strong open-source large language model.",
-            id: "nvidia/Llama-3.1-Nemotron-70B-Instruct",
+            description: "Text generation model used to write code.",
+            id: "Qwen/Qwen2.5-Coder-32B-Instruct",
         },
     ],
     spaces: [

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

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

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

@@ -8,6 +8,10 @@ const taskData = {
             description: "Conceptual Captions is a dataset consisting of ~3.3M images annotated with captions.",
             id: "conceptual_captions",
         },
+        {
+            description: "12M image-caption pairs.",
+            id: "Spawning/PD12M",
+        },
     ],
     demo: {
         inputs: [

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

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

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

@@ -10,7 +10,7 @@ const taskData = {
             id: "mythicinfinity/libritts_r",
         },
         {
-            description: "Mulit-lingual dataset.",
+            description: "Multi-lingual dataset.",
             id: "facebook/multilingual_librispeech",
         },
     ],
@@ -46,25 +46,25 @@ const taskData = {
         },
         {
             description: "A massively multi-lingual TTS model.",
-            id: "coqui/XTTS-v2",
+            id: "fishaudio/fish-speech-1.5",
         },
         {
             description: "A powerful TTS model.",
-            id: "amphion/MaskGCT",
+            id: "OuteAI/OuteTTS-0.1-350M",
         },
         {
-            description: "A Llama based TTS model.",
-            id: "OuteAI/OuteTTS-0.1-350M",
+            description: "Small yet powerful TTS model.",
+            id: "hexgrad/Kokoro-82M",
         },
     ],
     spaces: [
         {
-            description: "An application for generate highly realistic, multilingual speech.",
-            id: "suno/bark",
+            description: "An application for generate high quality speech in different languages.",
+            id: "hexgrad/Kokoro-TTS",
         },
         {
-            description: "An application on XTTS, a voice generation model that lets you clone voices into different languages.",
-            id: "coqui/xtts",
+            description: "A multilingual text-to-speech application.",
+            id: "fishaudio/fish-speech-1",
         },
         {
             description: "An application that generates speech in different styles in English and Chinese.",

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

@@ -61,15 +61,15 @@ const taskData = {
     models: [
         {
             description: "A strong model for consistent video generation.",
-            id: "rain1011/pyramid-flow-sd3",
+            id: "tencent/HunyuanVideo",
         },
         {
-            description: "A robust model for text-to-video generation.",
-            id: "VideoCrafter/VideoCrafter2",
+            description: "A text-to-video model with high fidelity motion and strong prompt adherence.",
+            id: "Lightricks/LTX-Video",
         },
         {
-            description: "A cutting-edge text-to-video generation model.",
-            id: "TIGER-Lab/T2V-Turbo-V2",
+            description: "A text-to-video model focusing on physics-aware applications like robotics.",
+            id: "nvidia/Cosmos-1.0-Diffusion-7B-Text2World",
         },
     ],
     spaces: [

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

@@ -36,12 +36,12 @@ const taskData = {
     metrics: [],
     models: [
         {
-            description: "A robust video-text-to-text model that can take in image and video inputs.",
-            id: "llava-hf/llava-onevision-qwen2-72b-ov-hf",
+            description: "A robust video-text-to-text model.",
+            id: "Vision-CAIR/LongVU_Qwen2_7B",
         },
         {
-            description: "Large and powerful video-text-to-text model that can take in image and video inputs.",
-            id: "llava-hf/LLaVA-NeXT-Video-34B-hf",
+            description: "Strong video-text-to-text model with reasoning capabilities.",
+            id: "GoodiesHere/Apollo-LMMs-Apollo-7B-t32",
         },
     ],
     spaces: [

package/dist/esm/tasks/zero-shot-classification/data.js

@@ -53,8 +53,8 @@ const taskData = {
             id: "facebook/bart-large-mnli",
         },
         {
-            description: "Powerful zero-shot multilingual text classification model that can accomplish multiple tasks.",
-            id: "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
+            description: "Cutting-edge zero-shot multilingual text classification model.",
+            id: "MoritzLaurer/ModernBERT-large-zeroshot-v2.0",
         },
     ],
     spaces: [],

package/dist/esm/tasks/zero-shot-image-classification/data.d.ts.map

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