Hackernews posts about Llama3.1 405B
- Show HN: Run Llama3.1 405B on a 8GB VRAM challenge [video] (www.youtube.com)
- llama3.1-405B leaked at 3am the day before on 4chan (twitter.com)
- Using Llama3.1 405B to generate political synthetic data (www.oxen.ai)
- CentML gives free access to llama3.1-405B (cserve-llama.centml.com)
- We fine-tuned Llama 405B on AMD GPUs (publish.obsidian.md)