VideoLLaMA2.1-7B-16F
VideoLLaMA2.1-7B-16F (DAMO-NLP-SG, 2024) is a 7 billion parameter video-generation model. VideoLLaMA2.1-7B-16F is an open-weights video model with roughly 7 billion parameters.
by DAMO-NLP-SG · 7B parameters
Best for
Ways to use VideoLLaMA2.1-7B-16F in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your DAMO-NLP-SG API key. osFoundry discovers VideoLLaMA2.1-7B-16F 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
VideoLLaMA2.1-7B-16F 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.
What hardware can run VideoLLaMA2.1-7B-16F
VideoLLaMA2.1-7B-16F runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~17 GB).
VideoLLaMA2.1-7B-16F vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about VideoLLaMA2.1-7B-16F
Is VideoLLaMA2.1-7B-16F free to use?
VideoLLaMA2.1-7B-16F 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 VideoLLaMA2.1-7B-16F commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does VideoLLaMA2.1-7B-16F need?
Approximately 5 GB at Q4 quantisation, or 17 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run VideoLLaMA2.1-7B-16F locally?
Yes. VideoLLaMA2.1-7B-16F is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is VideoLLaMA2.1-7B-16F best at?
VideoLLaMA2.1-7B-16F is well-suited to video text to text.
How do I use VideoLLaMA2.1-7B-16F in osFoundry?
Paste your DAMO-NLP-SG API key in the key dialog (or deploy the open weights for self-hostable models), assign VideoLLaMA2.1-7B-16F to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by DAMO-NLP-SG on October 14, 2024. Source: https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-16F