There are also some LLaMA LoRAs that are trained on the Anthropic dataset specif...

int_19h on March 24, 2023 | parent | context | favorite | on: LoRA: Low-Rank Adaptation of Large Language Models

There are also some LLaMA LoRAs that are trained on the Anthropic dataset specifically for chat:

I haven't done any formal tests on this yet, but with llama-13b, the overall structure of its responses definitely becomes much more ChatGPT-like. It would be very interesting to see how the 65B model performs.