Llama 3.3 70B Instruct
Suveräänsus ja majutamine
See mudel on loetletud viitamiseks. Seda ei majutata veel LLM EU-s ega teeninda seda siin ükski esimese osapoole lõpp-punkt. Päringud suunatakse otse pakkujale, pakkuja enda tingimustel.
Kokkuvõte
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.
Tehnilised andmed
- Pakkuja
- Meta (US)
- Konteksti aken
- 131k
- Parameetrid
- 70.55B
- Modaalsused
- text
- Litsents
- llama3.3 · licence
- Avatud kaalud
- yes
- Avaldamiskuupäev
- 06. dets 2024
- Ülesanded
- reasoning, summarization, multilingual-support, rag
Keeled
Tugev: en, de, fr, it, pt, es
Piisav: hi, th
Keeled
Tugev
- en
- de
- fr
- it
- pt
- es
Piisav
- hi
- th
Verifitseerimata: pakkuja ei ole seda väidet dokumenteerinud. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Millal kasutada
Tugevused
- 70B dense quality at a fraction of 405B serving cost
- 128k-token context window
- mature quantisation and serving support
Piirangud
- Llama 3.3 Community License with a 700M MAU threshold and acceptable-use policy
- text-only, no image input
- needs multiple accelerators at BF16