Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Llama awoṣe Ìdílé adanwo

Review Llama’s open-weight releases, model lineage, instruction tuning, inference efficiency, and newer multimodal variants.

Jẹmọ itọsọna awọn ọnaÌdílé Awoṣe Llama
Ibeere 1 ti 8

How does Meta describe access to Llama model weights, and what governs use?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. How does Meta describe access to Llama model weights, and what governs use?
    • Weights are publicly released for eligible versions, subject to each version’s license and use terms
    • Every version is public domain with unrestricted use
    • Only Meta employees can access any Llama weights
    • The weights are downloadable without any terms
  2. Kini adape 'Llama' duro fun?
    • Ẹkọ Laini Ati Itumọ Multimodal
    • Awoṣe Ede nla Meta AI
    • Layered kannaa Ati Machine Analysis
    • Ohun elo Isakoso Ede Agbegbe
  3. Itusilẹ Llama wo ni akọkọ ṣafikun iwe-aṣẹ ti o fun laaye ni lilo iṣowo gbooro?
    • Llama atilẹba 1
    • Llama 405 nikan
    • Llama 2
    • Ko si ọkan ninu wọn gba lilo iṣowo
  4. Kini faaji labẹ awọn awoṣe Llama?
    • A convolutional image classifier
    • A akojọpọ igi ipinnu
    • Nẹtiwọọki loorekoore laisi akiyesi
    • Ayipada koodu-nikan ti n sọ asọtẹlẹ ami atẹle
  5. Bawo ni Llama 'iwiregbe' tabi awọn iyatọ aifwy ilana ṣe ṣe lati tẹle awọn itọsi olumulo?
    • Nipasẹ iṣatunṣe itanran ti iṣakoso ati ikẹkọ imudara lati awọn esi eniyan
    • Nipa jijẹ iwọn iboju
    • Nipa piparẹ awoṣe ipilẹ patapata
    • Nipa titumọ gbogbo awọn itọka si Latin ni akọkọ
  6. In what deployment setup can running Llama locally avoid sending prompts to a hosted inference service?
    • Whenever a model is downloaded, even when an app sends prompts to cloud tools
    • When inference runs on-device or on a private local server without a prompt-forwarding service
    • Only when the model is fine-tuned rather than used for inference
    • When the application stores prompts in a shared hosted API
  7. Which attention design did Meta adopt in Llama 3 8B and 70B to improve inference efficiency?
    • Residual vector quantization
    • Spatially-adaptive normalization
    • Grouped-query attention (GQA)
    • A recurrent state-space scan
  8. What inputs can Llama 3.2 Vision models accept?
    • Audio waveforms only
    • Video frames only, with no text
    • Sensor data without language or images
    • Text and images