LLaMA 2 just released!

🚨🔔 Meta just released LLaMa 2, the new state-of-the-art open-source LLM

✅ LLaMA 2 is the next iteration of LLaMA and comes with a commercial-friendly license.😍

✅ LLaMA 2 comes in 3 different model sizes 7B, 13B, and 70B. The 7B & 13B are leveraging the same architecture as LLaMA 1 and are a 1-to-1 replacement for commercial use!

New and improvements to v1:

🔠 Trained on 2T Tokens

💰Commercial use allowed ✅

💬 Chat models for dialogue use cases

🪟 4096 default context window (can be increased)

🧮 7B, 13B & 70B parameter version

🧠 70B model adopted grouped-query attention (GQA)

🛠 Chat models can use tools & plugins

🚀 LLaMA 2-CHAT as good as OpenAI ChatGPT

🤗 Available on Hugging Face

Announcement: https://ai.meta.com/llama/

Paper: https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/

Models: https://huggingface.co/models?other=llama-2

It's exciting to see Meta going fully open allowing commercial use 🔥 The gap between closed-source is melting.🧊