not-for-all-audiences llama llama-2 meta pytorch transformers text-generation storytelling storywriting stories writing

Join the Coffee & AI Discord for AI Stuff and things! Discord

This is a model merge of https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b + https://huggingface.co/nRuaif/Kimiko_13B) Lora merge was done at full weight (1:1 ratio)

Credit to DoctorShotgun for the merge idea.

Quantization format is GPTQ 128 Act Order + Desc Act