{"id":968,"slug":"meaecosystem--pustaka","name":"pustaka","author":"meaecosystem","description":"\n\n\n\n\n\n 🇮🇩 Bahasa Indonesia  ·  🇬🇧 English  ·  🇯🇵 日本語  ·  🇨🇳 中文  ·  🇰🇷 한국어 \n\n\n\n\n\t\n\t\t\n\t\n\t\n\t\tBahasa Indonesia\n\t\n\nPustaka adalah korpus teks terbuka berskala besar yang dikembangkan oleh MEA Ecosystem, dimulai dengan fokus penuh pada Bahasa Indonesia. Corpus ini disusun dari beberapa sumber publik berkualitas — web crawl yang telah difilter, ensiklopedia, berita, forum, hingga lexicon bahasa gaul — lalu diproses ulang melalui pipeline pembersihan (deteksi bahasa, filter panjang dokumen… See the full description on the dataset page: https://huggingface.co/datasets/meaecosystem/pustaka.","tags":"[\"Task_categories:text-Generation\",\"Language:id\",\"Language:en\",\"Language:ja\",\"Language:zh\",\"Language:ko\"]","license":null,"framework":null,"parameters":null,"downloads":89099,"likes":3,"verified":0,"created_at":"2026-10-07 13:23:40","updated_at":"2026-10-07 13:23:40","source_url":"https://huggingface.co/datasets/meaecosystem/pustaka","source_platform":"huggingface","hf_repo_id":"meaecosystem/pustaka","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":967,"model_id":968,"version":"v1.0.0","manifest_hash":"c3ede120eca3293767157d8b98a809eac9d0508f7ecdff4b2ae0dc27afbb2026","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/meaecosystem--pustaka/v1.0.0.json","created_at":"2026-10-07 13:23:40"}],"files":[],"signatures":[{"id":1540,"version_id":967,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"7d7ca0f185806f2afb8d7db0d836c8d8d928c22ba91ece65cce6b1df02b92a2f","attestation_type":"registry","signed_at":"2026-10-07 13:23:40"}],"hndl":null}