Qabbel
Llama 3.2 3B Instruct vs Llama 3.2 11B Vision Instruct
Qiegħed żewġ mudelli sa erbgħa ma' xulxin fuq l-oqsma li jiddeċiedu deployment: kuntest, prezz, reġjun, liċenzja, lingwi, hosting, u x'hu verifikat.
| Llama 3.2 3B Instruct | Llama 3.2 11B Vision Instruct | |
|---|---|---|
| Fornitur | Meta | Meta |
| Parametri | 3.2B | 10.7B |
| Tieqa tal-kuntest | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. | Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni. |
| Liċenzja | llama3.2 | llama3.2 |
| Modalitajiet | text | text, vision |
| Data tar-rilaxx | 18 Set 2024 | 18 Set 2024 |
| Lingwi | Qawwi: en, de, fr, it, pt, es Adekwat: hi, th | Qawwi: en, de, fr, it, pt, es Adekwat: hi, th |
| Piżijiet miftuħa | iva | iva |
| Kompiti | Spiża baxxa, Appoġġ multilingwi, Sommarizzazzjoni | Viżjoni, Appoġġ multilingwi |
Fejn żewġ mudelli jvarjaw, din it-tabella turi d-differenza u tieqaf. LLM EU ma tippubblikax badge ta' rebbieħ mingħajr punteġġ dokumentat għal dik il-kompitu, u figura nieqsa tibqa' nieqsa minflok ma ssir żero.
Meta tużah
Llama 3.2 3B Instruct
Saħħiet
- 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
Limiti
- 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
Kompiti
Llama 3.2 11B Vision Instruct
Saħħiet
- 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
Limiti
- 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
Kompiti
Kompiti: Appoġġ multilingwi