{"id":381,"slug":"huggingfacem4--finevision","name":"FineVision","author":"HuggingFaceM4","description":"\n\t\n\t\t\n\t\tFine Vision\n\t\n\n\nFineVision is a massive collection of datasets with 17.3M images, 24.3M samples, 88.9M turns, and 9.5B answer tokens, designed for training state-of-the-art open Vision-Language-Models.\nMore detail can be found in the blog post: https://huggingface.co/spaces/HuggingFaceM4/FineVision\n\n\t\n\t\t\n\t\n\t\n\t\tLoad the data\n\t\n\n  from datasets import load_dataset, get_dataset_config_names\n\n  # Get all subset names and load the first one\n  available_subsets =… See the full description on the dataset page: https://huggingface.co/datasets/HuggingFaceM4/FineVision.","tags":"[\"Size_categories:10M<n<100M\",\"Format:parquet\",\"Modality:image\",\"Modality:text\",\"Library:datasets\",\"Library:dask\"]","license":null,"framework":null,"parameters":null,"downloads":102192,"likes":484,"verified":0,"created_at":"2026-04-21 03:46:27","updated_at":"2026-05-08 06:10:30","source_url":"https://huggingface.co/datasets/HuggingFaceM4/FineVision","source_platform":"huggingface","hf_repo_id":"HuggingFaceM4/FineVision","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":380,"model_id":381,"version":"v1.0.0","manifest_hash":"570a8b5424b6ce9207fdaa720e05b7d803a2d38fce603b47fae6c3d650ff3128","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/huggingfacem4--finevision/v1.0.0.json","created_at":"2026-04-21 03:46:27"}],"files":[],"signatures":[{"id":837,"version_id":380,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"32ac328b63f4999928236ee02e2efe13a83b172428aaebefad7bb028e8cbef15","attestation_type":"registry","signed_at":"2026-04-21 03:46:27"}],"hndl":null}