diff-codegen-6b-v2
diff-codegen-6b-v2 is a 6 billion parameter chat model from CarperAI, released January 23, 2023. diff-codegen-6b-v2 is an open-weights chat model with roughly 6 billion parameters.
by CarperAI · 6B parameters
Best for
Ways to use diff-codegen-6b-v2 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your CarperAI API key. osFoundry discovers diff-codegen-6b-v2 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
diff-codegen-6b-v2 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 diff-codegen-6b-v2
diff-codegen-6b-v2 runs on a single 16GB consumer GPU (~4 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~15 GB).
diff-codegen-6b-v2 vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about diff-codegen-6b-v2
Is diff-codegen-6b-v2 free to use?
diff-codegen-6b-v2 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 diff-codegen-6b-v2 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 diff-codegen-6b-v2 need?
Approximately 4 GB at Q4 quantisation, or 15 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run diff-codegen-6b-v2 locally?
Yes. diff-codegen-6b-v2 is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is diff-codegen-6b-v2 best at?
diff-codegen-6b-v2 is well-suited to text generation.
How do I use diff-codegen-6b-v2 in osFoundry?
Paste your CarperAI API key in the key dialog (or deploy the open weights for self-hostable models), assign diff-codegen-6b-v2 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by CarperAI on January 23, 2023. Source: https://huggingface.co/CarperAI/diff-codegen-6b-v2