Llama 3.3 70B Instruct

Meta

Katalgu biss Piżijiet miftuħa

Sovranità u hosting

Katalgu biss

Dan il-mudell huwa katalogat għal referenza. Mhuwiex ospitat fuq LLM EU bħalissa, u l-ebda endpoint tal-ewwel parti ma jservih hawn. Talbiet lejh imorru direttament għand il-fornitur, taħt it-termini tal-fornitur stess.

Sommarju

Llama 3.3 70B Instruct is the December 2024 refresh of Meta’s 70B instruct model, with a 128k-token context window and the same Llama 3.3 Community License terms as Llama 3.1. Meta positions it as an alternative to the larger Llama 3.1 405B for general assistant work. It is text-only and is the largest dense Llama checkpoint still in common self-hosted use.

Speċifikazzjonijiet

Fornitur
Meta (US)
Tieqa tal-kuntest
131k
Parametri
70.55B
Modalitajiet
text
Liċenza
llama3.3 · licence
Piżijiet miftuħa
yes
Data tal-ħruġ
06 Diċ 2024
Kompiti
reasoning, summarization, multilingual-support, rag

Lingwi

Qawwi: en, de, fr, it, pt, es

Adekwat: hi, th

Lingwi

Qawwi

  • en
  • de
  • fr
  • it
  • pt
  • es

Adekwat

  • hi
  • th

Mhux verifikat: il-fornitur ma dokumentax din id-dikjarazzjoni. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

Meta tużaha

Saħħiet

  • 70B dense quality at a fraction of 405B serving cost
  • 128k-token context window
  • mature quantisation and serving support

Limiti

  • Llama 3.3 Community License with a 700M MAU threshold and acceptable-use policy
  • text-only, no image input
  • needs multiple accelerators at BF16