mdeberta-v3-base-squad2
mdeberta-v3-base-squad2 is a chat model from timpal0l, released November 30, 2022. mdeberta-v3-base-squad2 is an open-weights chat model.
by timpal0l
Best for
Ways to use mdeberta-v3-base-squad2 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your timpal0l API key. osFoundry discovers mdeberta-v3-base-squad2 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
mdeberta-v3-base-squad2 is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
mdeberta-v3-base-squad2 vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| mdeberta-v3-base-squad2 | timpal0l | — | — | Free (local) | Yes |
| surya_layout3 | vikp | — | — | Free (local) | Yes |
| subwiz | HadrianSecurity | — | — | Free (local) | Yes |
| unik3d-vitl | lpiccinelli | — | — | Free (local) | Yes |
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about mdeberta-v3-base-squad2
Is mdeberta-v3-base-squad2 free to use?
mdeberta-v3-base-squad2 is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use mdeberta-v3-base-squad2 commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run mdeberta-v3-base-squad2 locally?
Yes. mdeberta-v3-base-squad2 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is mdeberta-v3-base-squad2 best at?
mdeberta-v3-base-squad2 is well-suited to question answering.
How do I use mdeberta-v3-base-squad2 in osFoundry?
Paste your timpal0l API key in the key dialog (or deploy the open weights for self-hostable models), assign mdeberta-v3-base-squad2 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by timpal0l on November 30, 2022. Source: https://huggingface.co/timpal0l/mdeberta-v3-base-squad2