LLaMA2 is out!

- can be used commercially (under conditions, but mostly freely)
- fine-tuned chat version
- llama.cpp quantized version is available (see links below)

Waiting for gpt4all implementation for lazy person (me) and let's play!

More about the model:
https://about.fb.com/news/2023/07/llama-2/

GGML versions for llama.cpp:

https://huggingface.co/TheBloke/Llama-2-7B-GGML
https://huggingface.co/TheBloke/Llama-2-13B-GGML
https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML
https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML