Llama 3 announced

Llama 3 announced.

* 8B and 70B models and instruction-tuned versions are available.
* Trained on more than 15T tokens, 7x+ larger than Llama 2's dataset!
* 8k context window
* New trust and safety tools with Llama Guard 2, Code Shield, and CyberSec Eval 2.

In the coming months, Meta plans to introduce new capabilities, longer context windows, additional model sizes, and enhanced performance.

https://llama.meta.com/llama3/