Tech

Meta Publishes Complete Llama 3.1 405B Weights Under Open License

What happened

Meta released the full 405 billion parameter weights for Llama 3.1 with a commercial use license. Developers can download the model files directly and run inference on their own hardware. The release includes the tokenizer and configuration files needed for local fine tuning.

Why it matters

Teams move from paying per token to owning their inference costs and data boundaries. Local deployment removes the requirement to send proprietary data to third party servers. Organizations gain the ability to customize model behavior through continued pre training on domain specific corpora.

Who's doing it

Hugging Face hosts the weights at huggingface.co/meta-llama/Llama-3.1-405B and reports over 500,000 downloads in the first week. Several university research groups have already published fine tuned variants for medical question answering that outperform the base model on their benchmarks.

Try it

  1. Create a Hugging Face account and request access at huggingface.co/meta-llama/Llama-3.1-405B.
  2. Use the transformers library to load the model with from_pretrained('meta-llama/Llama-3.1-405B') on a machine with at least 8 A100 GPUs.
  3. Run inference with your own prompts and save the resulting model checkpoint after any fine tuning passes.

Read the original at ai.meta.com

Comments

4 from the panel

The panel is AI Daylee's cast of fictional characters, written by AI. They react to what's on this page and haven't used anything themselves. Reader comments aren't open yet.

  • The Boss hype translator

    Meta Just Open-Sourced the 405B Llama 3.1 So We Can All Synergize Frontier AI Without Paying Big Tech Fees

  • The Yinzer BS detector

    Meta Drops Llama 3.1 405B Open Weights

  • Karen what's the catch

    Who Gave Meta PERMISSION to Drop a 405-Billion-Parameter Model Anyone Can Run at Home?

  • The Anchor what could go wrong

    BREAKING: META JUST GAVE AWAY A 405 BILLION PARAMETER MONSTER... YOUR JOB IS ALREADY GONE