@huggingface/tasks 0.13.15 → 0.13.16

package/dist/commonjs/local-apps.js

@@ -29,17 +29,17 @@ function isMlxModel(model) {
     return model.tags.includes("mlx");
 }
 const snippetLlamacpp = (model, filepath) => {
+    let tagName = "";
+    if (filepath) {
+        const quantLabel = (0, gguf_js_1.parseGGUFQuantLabel)(filepath);
+        tagName = quantLabel ? `:${quantLabel}` : "";
+    }
     const command = (binary) => {
-        const snippet = [
-            "# Load and run the model:",
-            `${binary} \\`,
-            `  --hf-repo "${model.id}" \\`,
-            `  --hf-file ${filepath ?? "{{GGUF_FILE}}"} \\`,
-            `  -p "${model.tags.includes("conversational") ? "You are a helpful assistant" : "Once upon a time,"}"`,
-        ];
-        if (model.tags.includes("conversational")) {
+        const snippet = ["# Load and run the model:", `${binary} -hf ${model.id}${tagName}`];
+        if (!model.tags.includes("conversational")) {
+            // for non-conversational models, add a prompt
             snippet[snippet.length - 1] += " \\";
-            snippet.push("  --conversation");
+            snippet.push('  -p "Once upon a time,"');
         }
         return snippet.join("\n");
     };

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

@@ -12,11 +12,7 @@ const local_apps_js_1 = require("./local-apps.js");
         };
         const snippet = snippetFunc(model);
         (0, vitest_1.expect)(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli \\
-  --hf-repo "bartowski/Llama-3.2-3B-Instruct-GGUF" \\
-  --hf-file {{GGUF_FILE}} \\
-  -p "You are a helpful assistant" \\
-  --conversation`);
+llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF`);
     });
     (0, vitest_1.it)("llama.cpp non-conversational", async () => {
         const { snippet: snippetFunc } = local_apps_js_1.LOCAL_APPS["llama.cpp"];
@@ -27,9 +23,7 @@ llama-cli \\
         };
         const snippet = snippetFunc(model);
         (0, vitest_1.expect)(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli \\
-  --hf-repo "mlabonne/gemma-2b-GGUF" \\
-  --hf-file {{GGUF_FILE}} \\
+llama-cli -hf mlabonne/gemma-2b-GGUF \\
   -p "Once upon a time,"`);
     });
     (0, vitest_1.it)("vLLM conversational llm", async () => {

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

@@ -36,10 +36,6 @@ 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/commonjs/tasks/fill-mask/data.js

@@ -59,8 +59,8 @@ 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/commonjs/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/commonjs/tasks/image-classification/data.js

@@ -74,9 +74,8 @@ 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/commonjs/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/commonjs/tasks/image-feature-extraction/data.js

@@ -42,15 +42,20 @@ 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/commonjs/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/commonjs/tasks/image-text-to-text/data.js

@@ -7,8 +7,8 @@ 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.",
@@ -42,11 +42,15 @@ 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",
         },
         {
@@ -58,8 +62,8 @@ 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.",
@@ -83,14 +87,18 @@ 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/commonjs/tasks/image-to-3d/data.js

@@ -41,8 +41,8 @@ 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: [
@@ -55,8 +55,8 @@ 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/commonjs/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/commonjs/tasks/image-to-image/data.js

@@ -10,6 +10,10 @@ 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: [
@@ -50,16 +54,20 @@ 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/commonjs/tasks/index.js

@@ -69,7 +69,7 @@ exports.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/commonjs/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/commonjs/tasks/keypoint-detection/data.js

@@ -31,6 +31,10 @@ 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/commonjs/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/commonjs/tasks/object-detection/data.js

@@ -52,6 +52,10 @@ 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: [
         {
@@ -63,8 +67,8 @@ 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/commonjs/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/commonjs/tasks/sentence-similarity/data.js

@@ -66,9 +66,13 @@ 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/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,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/commonjs/tasks/text-generation/data.js

@@ -3,24 +3,28 @@ Object.defineProperty(exports, "__esModule", { value: true });
 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: {
@@ -59,20 +63,20 @@ 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/commonjs/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/commonjs/tasks/text-to-image/data.js

@@ -10,6 +10,10 @@ 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/commonjs/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/commonjs/tasks/text-to-speech/data.js

@@ -12,7 +12,7 @@ const taskData = {
             id: "mythicinfinity/libritts_r",
         },
         {
-            description: "Mulit-lingual dataset.",
+            description: "Multi-lingual dataset.",
             id: "facebook/multilingual_librispeech",
         },
     ],
@@ -48,25 +48,25 @@ 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/commonjs/tasks/text-to-video/data.js

@@ -63,15 +63,15 @@ 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/commonjs/tasks/video-text-to-text/data.js

@@ -38,12 +38,12 @@ 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/commonjs/tasks/zero-shot-classification/data.js

@@ -55,8 +55,8 @@ 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/commonjs/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"}

package/dist/commonjs/tasks/zero-shot-image-classification/data.js

@@ -48,16 +48,20 @@ const taskData = {
     ],
     models: [
         {
-            description: "Robust image classification model trained on publicly available image-caption data.",
-            id: "openai/clip-vit-base-patch16",
+            description: "Multilingual image classification model for 80 languages.",
+            id: "visheratin/mexma-siglip",
         },
         {
             description: "Strong zero-shot image classification model.",
             id: "google/siglip-so400m-patch14-224",
         },
         {
-            description: "Small yet powerful zero-shot image classification model that can run on edge devices.",
-            id: "apple/MobileCLIP-S1-OpenCLIP",
+            description: "Robust zero-shot image classification model.",
+            id: "microsoft/LLM2CLIP-EVA02-L-14-336",
+        },
+        {
+            description: "Powerful zero-shot image classification model supporting 94 languages.",
+            id: "jinaai/jina-clip-v2",
         },
         {
             description: "Strong image classification model for biomedical domain.",

package/dist/esm/local-apps.js

@@ -26,17 +26,17 @@ function isMlxModel(model) {
     return model.tags.includes("mlx");
 }
 const snippetLlamacpp = (model, filepath) => {
+    let tagName = "";
+    if (filepath) {
+        const quantLabel = parseGGUFQuantLabel(filepath);
+        tagName = quantLabel ? `:${quantLabel}` : "";
+    }
     const command = (binary) => {
-        const snippet = [
-            "# Load and run the model:",
-            `${binary} \\`,
-            `  --hf-repo "${model.id}" \\`,
-            `  --hf-file ${filepath ?? "{{GGUF_FILE}}"} \\`,
-            `  -p "${model.tags.includes("conversational") ? "You are a helpful assistant" : "Once upon a time,"}"`,
-        ];
-        if (model.tags.includes("conversational")) {
+        const snippet = ["# Load and run the model:", `${binary} -hf ${model.id}${tagName}`];
+        if (!model.tags.includes("conversational")) {
+            // for non-conversational models, add a prompt
             snippet[snippet.length - 1] += " \\";
-            snippet.push("  --conversation");
+            snippet.push('  -p "Once upon a time,"');
         }
         return snippet.join("\n");
     };

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

@@ -10,11 +10,7 @@ describe("local-apps", () => {
         };
         const snippet = snippetFunc(model);
         expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli \\
-  --hf-repo "bartowski/Llama-3.2-3B-Instruct-GGUF" \\
-  --hf-file {{GGUF_FILE}} \\
-  -p "You are a helpful assistant" \\
-  --conversation`);
+llama-cli -hf bartowski/Llama-3.2-3B-Instruct-GGUF`);
     });
     it("llama.cpp non-conversational", async () => {
         const { snippet: snippetFunc } = LOCAL_APPS["llama.cpp"];
@@ -25,9 +21,7 @@ llama-cli \\
         };
         const snippet = snippetFunc(model);
         expect(snippet[0].content).toEqual(`# Load and run the model:
-llama-cli \\
-  --hf-repo "mlabonne/gemma-2b-GGUF" \\
-  --hf-file {{GGUF_FILE}} \\
+llama-cli -hf mlabonne/gemma-2b-GGUF \\
   -p "Once upon a time,"`);
     });
     it("vLLM conversational llm", async () => {

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"}