--- language: - en library_name: transformers pipeline_tag: text-generation tags: - llama - llama-2 license: agpl-3.0 --- # Model Card: Nous-Hermes-limarp-l2-13B This is a merge between: - [Nous Hermes Llama 2 13b](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b) - [LimaRP llama 2 Lora](https://huggingface.co/lemonilia/limarp-llama2) from July 28, 2023 at a weight of 0.66. Quantizations provided by myself: - [GPTQ](https://huggingface.co/kingbri/Nous-Hermes-limarp-l2-13B-GPTQ) The merge was performed using [ez-trainer](https://github.com/CoffeeVampir3/ez-trainer) by CoffeeVampire/Blackroot The intended objective is to combine NH-2's reasoning and instruction-following capabilities with LimaRP's character roleplay capabilities. The LimaRP LoRA was merged at a weight of 0.66 since a merge of 1.00 destroyed most nuances of a character's personality due to the LoRA being too strong on the base model. There still may be edge cases. If so, please report them and the lora weight will be dropped. ## Usage: Since this is a merge between NH-2 and LimaRP, the following instruction formats should work: Alpaca 2: ``` ### Instruction: ### Response: ``` LimaRP instruction format: ``` <> <> <> ``` ## Bias, Risks, and Limitations The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form. ## Training Details This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.