Kuis Model Kepingan Salju Arktik

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

1. Perusahaan macam apa yang membuat model Arktik?
   • Perusahaan gudang data cloud
   • Sebuah studio permainan video
   • Sebuah produsen mobil
   • Jaringan media sosial
2. What architecture figures did Snowflake report for Arctic?
   • A single dense network with 17B total parameters
   • 480B total parameters, with about 17B active per token
   • 480B active parameters for every token
   • A rule-based model with no neural parameters
3. Fokus tugas apa yang membedakan Arktik dari chatbot konsumen pada umumnya?
   • Menghasilkan puisi dan lirik lagu
   • Bermain catur
   • Tugas perusahaan seperti pembuatan dan pengkodean SQL
   • Mengedit foto
4. Under what license did Snowflake release Arctic’s model weights?
   • Lisensi kepemilikan tertutup
   • Lisensi khusus berlangganan
   • Tidak ada lisensi sama sekali
   • Apache 2.0
5. How did Snowflake characterize Arctic’s training compute budget?
   • It reported roughly under $2 million for its training compute
   • It reported a cost over one billion dollars
   • It said no computers were used
   • It did not disclose any estimate
6. Untuk apa model Arctic Embed digunakan?
   • Menghasilkan gambar
   • Penelusuran, pengambilan, dan pemberdayaan generasi tambahan pengambilan
   • Mengompresi video
   • Mengontrol robot
7. Which routing strategy did Snowflake report Arctic uses to choose MoE experts?
   • All-expert routing
   • Round-robin scheduling across tokens
   • Top-2 gating
   • A fixed expert selected by token position
8. Which two types of Arctic language-model checkpoints did Snowflake release?
   • Image and audio only
   • Encoder and speech-vocoder only
   • Training and evaluation datasets only
   • Base and instruct-tuned