README.md

metadata

library_name: peft
base_model: unsloth/llama-2-7b

Model Card for Model ID

1PP LoRA created using https://huggingface.co/unsloth/llama-2-7b as a base model and custom dataset of RP chatlogs using 1PP format.

Special thanks to nRuaif for providing GGML adapter and assistance in training the LoRA.