| 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. | |