Usporedi
Llama 3.2 3B Instruct vs Llama 3.2 11B Vision Instruct
Stavite dva do četiri modela jedan pored drugoga na poljima koja odlučuju o implementaciji: kontekst, cijena, regija, licenca, jezici, hosting i što je verificirano.
| Llama 3.2 3B Instruct | Llama 3.2 11B Vision Instruct | |
|---|---|---|
| Pružatelj | Meta | Meta |
| Parametri | 3.2B | 10.7B |
| Prozor konteksta | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. | Nije provjereno: pružatelj nije dokumentirao ovu tvrdnju. |
| Licenca | llama3.2 | llama3.2 |
| Modaliteti | text | text, vision |
| Datum izdanja | 18. ruj 2024. | 18. ruj 2024. |
| Jezici | Jako: en, de, fr, it, pt, es Zadovoljavajuće: hi, th | Jako: en, de, fr, it, pt, es Zadovoljavajuće: hi, th |
| Otvoreni utezi | da | da |
| Zadaci | Niska cijena, Višejezična podrška, Sažimanje | Vizija, Višejezična podrška |
Kada se dva modela razlikuju, ova tablica pokazuje razliku i tu staje. LLM EU ne objavljuje značku pobjednika bez dokumentiranog rezultata za taj zadatak, a brojka koja nedostaje ostaje nedostajuća umjesto da postane nula.
Kada ga koristiti
Llama 3.2 3B Instruct
Prednosti
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- at 3.2B parameters it fits on a single accelerator
- the model page lists 6 languages the European Union publishes in, including en, de, fr, it
- instruction-tuned checkpoint with a chat template in the repository
Ograničenja
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 3.2B parameters, the weights fit on a single modest accelerator
Zadaci
Llama 3.2 11B Vision Instruct
Prednosti
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- at 10.7B parameters it fits on a single accelerator
- the model page lists 6 languages the European Union publishes in, including en, de, fr, it
- instruction-tuned checkpoint with a chat template in the repository
Ograničenja
- catalogue only — LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 10.7B parameters, self-hosting needs a single accelerator with enough memory for the weights
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Zadaci
Zadaci: Višejezična podrška