The zarakiquemparte/hermeslimarp-l2-7b is a 7 billion parameter language model based on the Llama 2 architecture, created by zarakiquemparte. It is a merge of Nous Hermes Llama2 7b and LimaRP LLama2 7B, designed to combine their respective strengths. This model supports both Alpaca 2 and LimaRP instruction formats, making it versatile for various conversational and instruction-following tasks.
Loading preview...
Model Overview
The zarakiquemparte/hermeslimarp-l2-7b is a 7 billion parameter language model built upon the Llama 2 architecture. It represents a strategic merge of two distinct base models: Nous Hermes Llama2 7b and LimaRP LLama2 7B. This merging process was executed using a custom script, aiming to integrate the capabilities of both foundational models.
Key Features & Usage
- Merged Architecture: Combines the characteristics of Nous Hermes and LimaRP, potentially offering a broader range of conversational and instruction-following abilities.
- Instruction Format Flexibility: Supports two popular instruction formats, allowing for adaptable integration into different workflows:
- Alpaca 2 Format:
### Instruction: <prompt> ### Response: <leave a newline blank for model to respond> - LimaRP Format:
<<SYSTEM>> <character card and system prompt> <<USER>> <prompt> <<AIBOT>> <leave a newline blank for model to respond>
- Alpaca 2 Format:
Limitations
- Factual Accuracy: This model is not intended for providing factual information or advice. Users should verify any critical information independently.
Reproducibility
- The model's creation process, involving the merging of Lora with the base models, is reproducible using the provided script.