Qabbel

Instructblip Flan T5 Xl vs Instructblip Vicuna 7B

Qiegħed żewġ mudelli sa erbgħa ma' xulxin fuq l-oqsma li jiddeċiedu deployment: kuntest, prezz, reġjun, liċenzja, lingwi, hosting, u x'hu verifikat.

Instructblip Flan T5 XlInstructblip Vicuna 7B
Fornitur SalesforceSalesforce
Parametri 4B7.9B
Tieqa tal-kuntest Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni.Mhux verifikat: il-fornitur ma ddokumentax din id-dikjarazzjoni.
Liċenzja mitother
Modalitajiet text, visiontext, vision
Data tar-rilaxx 28 Mej 202322 Mej 2023
Lingwi Qawwi: en
Adekwat: —
Qawwi: en
Adekwat: —
Piżijiet miftuħa ivaiva
Kompiti ViżjoniViżjoni

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

Instructblip Flan T5 Xl

Saħħiet

  • 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

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 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

Kompiti

Viżjoni

Instructblip Vicuna 7B

Saħħiet

  • 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

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 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

Kompiti

Viżjoni

Kompiti: Viżjoni

Qabbel mudelli

Qabbel mudelli →