DS-Archive/Nous-Hermes-Llama2-13b-Limarp-Lora-Merged
DS-Archive/Nous-Hermes-Llama2-13b-Limarp-Lora-Merged is a 13 billion parameter Llama 2-based model, merging Nous Hermes Llama 2 13b with the LIMARP Lora adapter. This model is designed to combine strong reasoning and instruction-following capabilities with enhanced character roleplay. It is primarily intended for applications requiring both coherent instruction adherence and nuanced character interaction.
Loading preview...
Model Overview
DS-Archive/Nous-Hermes-Llama2-13b-Limarp-Lora-Merged is a 13 billion parameter language model built upon the Llama 2 architecture. It is a merge of two distinct components: the Nous Hermes Llama 2 13b base model and the LIMARP Lora adapter. The primary objective of this merge was to integrate the robust reasoning and instruction-following abilities of Nous Hermes Llama 2 with the specialized character roleplay capabilities provided by LIMARP Lora.
Key Capabilities
- Combined Strengths: Aims to offer both strong instruction adherence and advanced character roleplay.
- Instruction Formats: Supports two distinct prompting formats:
- The Alpaca instruction format from the Nous Hermes Llama 2 base model.
- The LIMARP Lora instruction format, which includes a system prompt for character cards.
Intended Use Cases
This model is particularly suited for applications where a balance between following instructions accurately and engaging in detailed character-driven interactions is required. It can be used for:
- Interactive storytelling and narrative generation.
- Roleplaying scenarios with defined character personas.
- Instruction-following tasks that benefit from a more expressive or character-aware response style.
Limitations and Considerations
- Bias: May exhibit biases similar to those found in niche online roleplaying communities, in addition to biases from its base model.
- Factual Accuracy: Not designed for providing factual information or advice; its strength lies in creative and interactive text generation.