Palyginti
Phi 3 Mini 128K Instruct vs Phi 3.5 Vision Instruct
Sudėkite du–keturis modelius greta pagal laukus, kurie lemia diegimą: kontekstas, kaina, regionas, licencija, kalbos, talpinimas ir tai, kas patikrinta.
| Phi 3 Mini 128K Instruct | Phi 3.5 Vision Instruct | |
|---|---|---|
| Teikėjas | Microsoft | Microsoft |
| Parametrai | 3.8B | 4.1B |
| Konteksto langas | Nepatvirtinta: teikėjas nepagrindė šio teiginio. | Nepatvirtinta: teikėjas nepagrindė šio teiginio. |
| Licencija | mit | mit |
| Modalumai | text | text, vision |
| Išleidimo data | 2024-04-22 | 2024-08-16 |
| Kalbos | Stipri: en Pakankama: nlp | Stipri: — Pakankama: nlp |
| Atvirieji svoriai | taip | taip |
| Užduotys | Mąstymas, Apibendrinimas, Atkūrimas (RAG) | Vizija, Apibendrinimas |
Kai du modeliai skiriasi, ši lentelė parodo skirtumą ir sustoja. LLM EU neskelbia nugalėtojo ženklo be dokumentuoto tos užduoties balo, o trūkstamas skaičius lieka trūkstamas, o ne tampa nuliu.
Kada naudoti
Phi 3 Mini 128K Instruct
Stiprybės
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 3.8B parameters it fits on a single accelerator
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Apribojimai
- 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 3.8B parameters, the weights fit on a single modest accelerator
Užduotys
Phi 3.5 Vision Instruct
Stiprybės
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 4.1B parameters it fits on a single accelerator
- instruction-tuned checkpoint with a chat template in the repository
Apribojimai
- 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 4.1B parameters, the weights fit on a single modest accelerator
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model
Užduotys
Užduotys: Apibendrinimas