Meta AI just released version 2 of their open-source Llama language model. This new version was trained on more data (2 trillion tokens), supports longer context length (4096 tokens), and has a more permissive license than v1 which allows for commercial use.

Here’s a list of developments from the last day since Llama 2 was released:

• Llama2 chatbot – An open-source demo application built by the infra team at A16Z and powered by Streamlit, Replicate, and Fly.io.
• Llama 2 7B - a 7-billion parameter version, fine tuned for chat completions, running on Replicate. Smaller and faster than the 13B and 70B versions.
• Llama 2 13B - a 13-billion parameter version, fine tuned for chat completions, running on Replicate.
• Llama 2 70B - a 70-billion parameter version, fine tuned for chat completions, running on Replicate. Slower than the 7B and 13B versions, but more capable.
• llm-replicate - A Replicate plugin for llm, a CLI utility and Python library for interacting with large language models.
• sdk.vercel.ai - Vercel’s online playground for comparing language models, now with support for Llama 2.
• nat.dev - A free playground for trying out Llama 2 and other language models.
• Ollama - An open-source tool for running language models on macOS, now with support for Llama 2.
• Llama 2 7B fine tuning — You can now fine tune Llama 7B with Replicate.

Follow us on Twitter to keep up with developments from the llamaverse.