UNPKG

@huggingface/tasks

Version:
66 lines (63 loc) 1.99 kB
import type { TaskDataCustom } from "../index.js"; const taskData: TaskDataCustom = { datasets: [ { description: "A dataset with multiple modality input and output pairs.", id: "PKU-Alignment/align-anything", }, ], demo: { inputs: [ { filename: "any-to-any-input.jpg", type: "img", }, { label: "Text Prompt", content: "What is the significance of this place?", type: "text", }, ], outputs: [ { label: "Generated Text", content: "The place in the picture is Osaka Castle, located in Osaka, Japan. Osaka Castle is a historic castle that was originally built in the 16th century by Toyotomi Hideyoshi, a powerful warlord of the time. It is one of the most famous landmarks in Osaka and is known for its distinctive white walls and black roof tiles. The castle has been rebuilt several times over the centuries and is now a popular tourist attraction, offering visitors a glimpse into Japan's rich history and culture.", type: "text", }, { filename: "any-to-any-output.wav", type: "audio", }, ], }, metrics: [], models: [ { description: "Strong model that can take in video, audio, image, text and output text and natural speech.", id: "Qwen/Qwen2.5-Omni-7B", }, { description: "Robust model that can take in image and text and generate image and text.", id: "deepseek-ai/Janus-Pro-7B", }, { description: "Any-to-any model with speech, video, audio, image and text understanding capabilities.", id: "openbmb/MiniCPM-o-2_6", }, { description: "A model that can understand image and text and generate image and text.", id: "EPFL-VILAB/4M-21_XL", }, ], spaces: [ { description: "An application to chat with an any-to-any (image & text) model.", id: "deepseek-ai/Janus-Pro-7B", }, ], summary: "Any-to-any models can understand two or more modalities and output two or more modalities.", widgetModels: [], youtubeId: "", }; export default taskData;