OpenAI's first open source language model since GPT-2
No thanks.
Submitted 3 weeks ago by ryujin470@fedia.io to technology@beehaw.org
https://www.theverge.com/openai/718785/openai-gpt-oss-open-model-release
OpenAI's first open source language model since GPT-2
paywall free version?
nathan@piefed.alphapuggle.dev 3 weeks ago
*if you have a laptop with 16gb of vram. Otherwise you'll be watching ollama hit your CPU for 5 minutes with no output
sefra1@lemmy.zip 3 weeks ago
Isn’t that true for most models until someone destiles and quantises them so they can run on common hardware?
fuckwit_mcbumcrumble@lemmy.dbzer0.com 3 weeks ago
This is the internet, we’re only allowed to be snarky here.
CyberSeeker@discuss.tchncs.de 3 weeks ago
Yes, but 20 billion parameters is too much for most GPUs, regardless of quantization. You would need at least 14GB, and even that’s unlikely without offloading major parts to the CPU and system RAM (which kills the token rate).
Ghoelian@lemmy.dbzer0.com 3 weeks ago
I mean yeah, but that doesn’t make the title any lore true.