@huggingface/tasks 0.13.15 → 0.13.17

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

@@ -46,16 +46,20 @@ 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/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.13.15",
+  "version": "0.13.17",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/local-apps.spec.ts

@@ -13,11 +13,7 @@ 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 () => {
@@ -30,9 +26,7 @@ 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,"`);
 	});
 

package/src/local-apps.ts

@@ -95,17 +95,17 @@ function isMlxModel(model: ModelData) {
 }
 
 const snippetLlamacpp = (model: ModelData, filepath?: string): LocalAppSnippet[] => {
+	let tagName = "";
+	if (filepath) {
+		const quantLabel = parseGGUFQuantLabel(filepath);
+		tagName = quantLabel ? `:${quantLabel}` : "";
+	}
 	const command = (binary: string) => {
-		const snippet = [
-			"# Load and run the model:",
-			`${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/src/model-data.ts

@@ -66,6 +66,9 @@ export interface ModelData {
 			base_model_name_or_path?: string;
 			task_type?: string;
 		};
+		keras_hub?: {
+			tasks?: string[];
+		};
 	};
 	/**
 	 * all the model tags

package/src/model-libraries-snippets.ts

@@ -95,6 +95,29 @@ export const bm25s = (model: ModelData): string[] => [
 retriever = BM25HF.load_from_hub("${model.id}")`,
 ];
 
+export const cxr_foundation = (model: ModelData): string[] => [
+	`!git clone https://github.com/Google-Health/cxr-foundation.git
+import tensorflow as tf, sys, requests
+sys.path.append('cxr-foundation/python/')
+
+# Install dependencies
+major_version = tf.__version__.rsplit(".", 1)[0]
+!pip install tensorflow-text=={major_version} pypng && pip install --no-deps pydicom hcls_imaging_ml_toolkit retrying
+
+# Load image (Stillwaterising, CC0, via Wikimedia Commons)
+from PIL import Image
+from io import BytesIO
+image_url = "https://upload.wikimedia.org/wikipedia/commons/c/c8/Chest_Xray_PA_3-8-2010.png"
+response = requests.get(image_url, headers={'User-Agent': 'Demo'}, stream=True)
+response.raw.decode_content = True # Ensure correct decoding
+img = Image.open(BytesIO(response.content)).convert('L') # Convert to grayscale
+
+# Run inference
+from clientside.clients import make_hugging_face_client
+cxr_client = make_hugging_face_client('cxr_model')
+print(cxr_client.get_image_embeddings_from_images([img]))`,
+];
+
 export const depth_anything_v2 = (model: ModelData): string[] => {
 	let encoder: string;
 	let features: string;
@@ -168,6 +191,28 @@ focallength_px = prediction["focallength_px"]`;
 	return [installSnippet, inferenceSnippet];
 };
 
+export const derm_foundation = (model: ModelData): string[] => [
+	`from huggingface_hub import from_pretrained_keras
+import tensorflow as tf, requests
+
+# Load and format input
+IMAGE_URL = "https://storage.googleapis.com/dx-scin-public-data/dataset/images/3445096909671059178.png"
+input_tensor = tf.train.Example(
+    features=tf.train.Features(
+        feature={
+            "image/encoded": tf.train.Feature(
+                bytes_list=tf.train.BytesList(value=[requests.get(IMAGE_URL, stream=True).content])
+            )
+        }
+    )
+).SerializeToString()
+
+# Load model and run inference
+loaded_model = from_pretrained_keras("google/derm-foundation")
+infer = loaded_model.signatures["serving_default"]
+print(infer(inputs=tf.constant([input_tensor])))`,
+]
+
 const diffusersDefaultPrompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k";
 
 const diffusers_default = (model: ModelData) => [
@@ -394,32 +439,103 @@ model = keras.saving.load_model("hf://${model.id}")
 `,
 ];
 
-export const keras_nlp = (model: ModelData): string[] => [
-	`# Available backend options are: "jax", "torch", "tensorflow".
-import os
-os.environ["KERAS_BACKEND"] = "jax"
+const _keras_hub_causal_lm = (modelId: string): string => `
+import keras_hub
 
-import keras_nlp
+# Load CausalLM model (optional: use half precision for inference)
+causal_lm = keras_hub.models.CausalLM.from_preset(${modelId}, dtype="bfloat16")
+causal_lm.compile(sampler="greedy")  # (optional) specify a sampler
 
-tokenizer = keras_nlp.models.Tokenizer.from_preset("hf://${model.id}")
-backbone = keras_nlp.models.Backbone.from_preset("hf://${model.id}")
-`,
-];
+# Generate text
+causal_lm.generate("Keras: deep learning for", max_length=64)
+`;
 
-export const keras_hub = (model: ModelData): string[] => [
-	`# Available backend options are: "jax", "torch", "tensorflow".
-import os
-os.environ["KERAS_BACKEND"] = "jax"
+const _keras_hub_text_to_image = (modelId: string): string => `
+import keras_hub
+
+# Load TextToImage model (optional: use half precision for inference)
+text_to_image = keras_hub.models.TextToImage.from_preset(${modelId}, dtype="bfloat16")
 
+# Generate images with a TextToImage model.
+text_to_image.generate("Astronaut in a jungle")
+`;
+
+const _keras_hub_text_classifier = (modelId: string): string => `
 import keras_hub
 
-# Load a task-specific model (*replace CausalLM with your task*)
-model = keras_hub.models.CausalLM.from_preset("hf://${model.id}", dtype="bfloat16")
+# Load TextClassifier model
+text_classifier = keras_hub.models.TextClassifier.from_preset(
+    ${modelId},
+    num_classes=2,
+)
+# Fine-tune
+text_classifier.fit(x=["Thilling adventure!", "Total snoozefest."], y=[1, 0])
+# Classify text
+text_classifier.predict(["Not my cup of tea."])
+`;
 
-# Possible tasks are CausalLM, TextToImage, ImageClassifier, ...
-# full list here: https://keras.io/api/keras_hub/models/#api-documentation
-`,
-];
+const _keras_hub_image_classifier = (modelId: string): string => `
+import keras_hub
+import keras
+
+# Load ImageClassifier model
+image_classifier = keras_hub.models.ImageClassifier.from_preset(
+    ${modelId},
+    num_classes=2,
+)
+# Fine-tune
+image_classifier.fit(
+    x=keras.random.randint((32, 64, 64, 3), 0, 256),
+    y=keras.random.randint((32, 1), 0, 2),
+)
+# Classify image
+image_classifier.predict(keras.random.randint((1, 64, 64, 3), 0, 256))
+`;
+
+const _keras_hub_tasks_with_example = {
+	CausalLM: _keras_hub_causal_lm,
+	TextToImage: _keras_hub_text_to_image,
+	TextClassifier: _keras_hub_text_classifier,
+	ImageClassifier: _keras_hub_image_classifier,
+};
+
+const _keras_hub_task_without_example = (task: string, modelId: string): string => `
+import keras_hub
+
+# Create a ${task} model
+task = keras_hub.models.${task}.from_preset(${modelId})
+`;
+
+const _keras_hub_generic_backbone = (modelId: string): string => `
+import keras_hub
+
+# Create a Backbone model unspecialized for any task
+backbone = keras_hub.models.Backbone.from_preset(${modelId})
+`;
+
+export const keras_hub = (model: ModelData): string[] => {
+	const modelId = model.id;
+	const tasks = model.config?.keras_hub?.tasks ?? [];
+
+	const snippets: string[] = [];
+
+	// First, generate tasks with examples
+	for (const [task, snippet] of Object.entries(_keras_hub_tasks_with_example)) {
+		if (tasks.includes(task)) {
+			snippets.push(snippet(modelId));
+		}
+	}
+	// Then, add remaining tasks
+	for (const task in tasks) {
+		if (!Object.keys(_keras_hub_tasks_with_example).includes(task)) {
+			snippets.push(_keras_hub_task_without_example(task, modelId));
+		}
+	}
+	// Finally, add generic backbone snippet
+	snippets.push(_keras_hub_generic_backbone(modelId));
+
+	return snippets;
+};
 
 export const llama_cpp_python = (model: ModelData): string[] => {
 	const snippets = [
@@ -845,6 +961,12 @@ model.${speechbrainMethod}("file.wav")`,
 	];
 };
 
+export const terratorch = (model: ModelData): string[] => [
+	`from terratorch.registry import BACKBONE_REGISTRY
+
+model = BACKBONE_REGISTRY.build("${model.id}")`,
+];
+
 export const transformers = (model: ModelData): string[] => {
 	const info = model.transformersInfo;
 	if (!info) {

package/src/model-libraries.ts

@@ -176,6 +176,7 @@ 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"`,
 	},
@@ -206,6 +207,7 @@ 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"`,
 	},
@@ -404,13 +406,6 @@ 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",
@@ -544,7 +539,10 @@ 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",
@@ -780,6 +778,15 @@ 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/src/tasks/audio-to-audio/data.ts

@@ -38,10 +38,6 @@ const taskData: TaskDataCustom = {
 		},
 	],
 	models: [
-		{
-			description: "A solid model of audio source separation.",
-			id: "speechbrain/sepformer-wham",
-		},
 		{
 			description: "A speech enhancement model.",
 			id: "ResembleAI/resemble-enhance",

package/src/tasks/fill-mask/data.ts

@@ -61,8 +61,8 @@ const taskData: TaskDataCustom = {
 	],
 	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/src/tasks/image-classification/data.ts

@@ -74,9 +74,8 @@ const taskData: TaskDataCustom = {
 	],
 	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:

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

@@ -43,15 +43,20 @@ const taskData: TaskDataCustom = {
 			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/src/tasks/image-text-to-text/about.md

@@ -24,12 +24,16 @@ Vision language models trained on image-text pairs can be used for visual questi
 
 ### Document Question Answering and Retrieval
 
-Documents often consist of different layouts, charts, tables, images, and more. Vision language models trained on formatted documents can extract information from them. This is an OCR-free approach; the inputs skip OCR, and documents are directly fed to vision language models.
+Documents often consist of different layouts, charts, tables, images, and more. Vision language models trained on formatted documents can extract information from them. This is an OCR-free approach; the inputs skip OCR, and documents are directly fed to vision language models. To find the relevant documents to be fed, models like [ColPali](https://huggingface.co/blog/manu/colpali) are used. An example workflow can be found [here](https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb).
 
 ### Image Recognition with Instructions
 
 Vision language models can recognize images through descriptions. When given detailed descriptions of specific entities, it can classify the entities in an image.
 
+### Computer Use
+
+Image-text-to-text models can be used to control computers with agentic workflows. Models like [ShowUI](https://huggingface.co/showlab/ShowUI-2B) and [OmniParser](https://huggingface.co/microsoft/OmniParser) are used to parse screenshots to later take actions on the computer autonomously.
+
 ## Inference
 
 You can use the Transformers library to interact with [vision-language models](https://huggingface.co/models?pipeline_tag=image-text-to-text&transformers). Specifically, `pipeline` makes it easy to infer models.
@@ -82,7 +86,8 @@ curl https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision
 ## Useful Resources
 
 - [Vision Language Models Explained](https://huggingface.co/blog/vlms)
-- [Open-source Multimodality and How to Achieve it using Hugging Face](https://www.youtube.com/watch?v=IoGaGfU1CIg&t=601s)
-- [Introducing Idefics2: A Powerful 8B Vision-Language Model for the community](https://huggingface.co/blog/idefics2)
+- [Welcome PaliGemma 2 – New vision language models by Google](https://huggingface.co/blog/paligemma2)
+- [SmolVLM - small yet mighty Vision Language Model](https://huggingface.co/blog/smolvlm)
+- [Multimodal RAG using ColPali and Qwen2-VL](https://github.com/merveenoyan/smol-vision/blob/main/ColPali_%2B_Qwen2_VL.ipynb)
 - [Image-text-to-text task guide](https://huggingface.co/tasks/image-text-to-text)
 - [Preference Optimization for Vision Language Models with TRL](https://huggingface.co/blog/dpo_vlm)

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

@@ -7,8 +7,8 @@ const taskData: TaskDataCustom = {
 			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.",
@@ -43,11 +43,15 @@ const taskData: TaskDataCustom = {
 	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",
 		},
 		{
@@ -59,8 +63,8 @@ const taskData: TaskDataCustom = {
 			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.",
@@ -84,14 +88,18 @@ const taskData: TaskDataCustom = {
 			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.",

package/src/tasks/image-to-3d/data.ts

@@ -41,8 +41,8 @@ const taskData: TaskDataCustom = {
 			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: TaskDataCustom = {
 			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/src/tasks/image-to-image/data.ts

@@ -10,6 +10,10 @@ const taskData: TaskDataCustom = {
 			description: "Multiple images of celebrities, used for facial expression translation",
 			id: "huggan/CelebA-faces",
 		},
+		{
+			description: "12M image-caption pairs.",
+			id: "Spawning/PD12M",
+		},
 	],
 	demo: {
 		inputs: [
@@ -53,17 +57,20 @@ const taskData: TaskDataCustom = {
 			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/src/tasks/index.ts

@@ -132,7 +132,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
 	"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/src/tasks/keypoint-detection/data.ts

@@ -31,6 +31,10 @@ const taskData: TaskDataCustom = {
 			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/src/tasks/object-detection/data.ts

@@ -54,6 +54,10 @@ const taskData: TaskDataCustom = {
 			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: [
 		{
@@ -65,8 +69,8 @@ const taskData: TaskDataCustom = {
 			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/src/tasks/sentence-similarity/data.ts

@@ -69,9 +69,13 @@ const taskData: TaskDataCustom = {
 			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: [
 		{