Sammenlign
Instructblip Flan T5 Xl vs Instructblip Vicuna 7B
Sæt to til fire modeller side om side på de felter, der afgør en udrulning: kontekst, pris, region, licens, sprog, hosting og hvad der er verificeret.
| Instructblip Flan T5 Xl | Instructblip Vicuna 7B | |
|---|---|---|
| Udbyder | Salesforce | Salesforce |
| Parametre | 4B | 7.9B |
| Kontekstvindue | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. | Ikke verificeret: udbyderen har ikke dokumenteret denne påstand. |
| Licens | mit | other |
| Modaliteter | text, vision | text, vision |
| Udgivelsesdato | 28. maj 2023 | 22. maj 2023 |
| Sprog | Stærk: en Tilstrækkelig: — | Stærk: en Tilstrækkelig: — |
| Åbne vægte | ja | ja |
| Opgaver | Vision | Vision |
Hvor to modeller adskiller sig, viser denne tabel forskellen og stopper. LLM EU offentliggør ikke et vinderbadge uden en dokumenteret score for den opgave, og et manglende tal forbliver manglende i stedet for at blive et nul.
Hvornår man bruger den
Instructblip Flan T5 Xl
Styrker
- 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 4B parameters it fits on a single accelerator
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Begrænsninger
- 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 4B 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
Opgaver
Instructblip Vicuna 7B
Styrker
- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- at 7.9B parameters it fits on a single accelerator
- the model page lists en
- instruction-tuned checkpoint with a chat template in the repository
Begrænsninger
- 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 other licence is a custom agreement whose commercial terms were not established from its published text, so commercial serving is not permitted until a human clears it; the router must not route to it
- the published configuration records no context window, so the card carries none
- at 7.9B 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
Opgaver
Opgaver: Vision