internlm2-chat-20b-ExPO
Built by chujiezheng, internlm2-chat-20b-ExPO is a 20 billion parameter chat model. internlm2-chat-20b-ExPO is an open-weights chat model with roughly 20 billion parameters.
by chujiezheng · 20B parameters
Best for
Ways to use internlm2-chat-20b-ExPO in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your chujiezheng API key. osFoundry discovers internlm2-chat-20b-ExPO 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
internlm2-chat-20b-ExPO 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 internlm2-chat-20b-ExPO
internlm2-chat-20b-ExPO runs on a single 16GB consumer GPU (~12 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~48 GB).
internlm2-chat-20b-ExPO vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about internlm2-chat-20b-ExPO
Is internlm2-chat-20b-ExPO free to use?
internlm2-chat-20b-ExPO 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 internlm2-chat-20b-ExPO 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 internlm2-chat-20b-ExPO need?
Approximately 12 GB at Q4 quantisation, or 48 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run internlm2-chat-20b-ExPO locally?
Yes. internlm2-chat-20b-ExPO is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is internlm2-chat-20b-ExPO best at?
internlm2-chat-20b-ExPO is well-suited to text generation.
How do I use internlm2-chat-20b-ExPO in osFoundry?
Paste your chujiezheng API key in the key dialog (or deploy the open weights for self-hostable models), assign internlm2-chat-20b-ExPO to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by chujiezheng on May 2, 2024. Source: https://huggingface.co/chujiezheng/internlm2-chat-20b-ExPO