{"id":717,"slug":"mvp-lab--llava-onevision-2-data","name":"LLaVA-OneVision-2-Data","author":"mvp-lab","description":"\n\t\n\t\t\n\t\n\t\n\t\tLLaVA-OneVision-2-Data\n\t\n\nTraining data for the LLaVA-OneVision-2 multimodal model family, covering large-scale video and spatial reasoning corpora used in mid-training.\n\n\t\n\t\t\n\t\n\t\n\t\tDataset Composition\n\t\n\n\n\t\n\t\t\nSubset\nFormat\nDescription\n\n\n\t\t\nmid_training_video/60s_rest/\nWebDataset (.tar)\n10,809 shards of ~60s video clips\n\n\nmid_training_video/caption_v0/split_30s.jsonl\nJSONL\nCaptions for 30-second video clips\n\n\nmid_training_video/caption_v0/split_60s.jsonl\nJSONL\nCaptions for… See the full description on the dataset page: https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-2-Data.","tags":"[\"Task_categories:video-Text-To-Text\",\"Task_categories:visual-Question-Answering\",\"Task_categories:image-Text-To-Text\",\"Language:en\",\"Size_categories:n<1K\",\"Format:parquet\"]","license":null,"framework":null,"parameters":null,"downloads":229270,"likes":30,"verified":0,"created_at":"2026-07-12 10:23:23","updated_at":"2026-07-12 14:23:34","source_url":"https://huggingface.co/datasets/mvp-lab/LLaVA-OneVision-2-Data","source_platform":"huggingface","hf_repo_id":"mvp-lab/LLaVA-OneVision-2-Data","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":716,"model_id":717,"version":"v1.0.0","manifest_hash":"4a591c41cef668a699c3607c16fbd069b23b067b27089adc2b7b5a0b65439c2e","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/mvp-lab--llava-onevision-2-data/v1.0.0.json","created_at":"2026-07-12 10:23:23"}],"files":[],"signatures":[{"id":1281,"version_id":716,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"2acfea7793591cb169fe401121289ae3ff49b396725cdfc9317332ea1e0a1ddc","attestation_type":"registry","signed_at":"2026-07-12 10:23:23"}],"hndl":null}