metadata

license: other
tags:
  - llama2

Model Card: ZaraXE L2 7b

This model uses Zarafusionex L2 7b without LimaRP (71%) as a base with Airoboros L2 7B GPT4 2.0 (29%) and the result of this merge was merged with LimaRP LLama2 7B Lora.

This merge of models(Zarafusionex w/o LimaRP and Airoboros) was done with this script

This merge of Lora with Model was done with this script

Merge illustration:

Usage:

Since this is a merge between Zarafusionex, Airoboros and LimaRP, the following instruction formats should work:

Alpaca 2:

### Instruction:
<prompt>

### Response:
<leave a newline blank for model to respond>

LimaRP instruction format:

<<SYSTEM>>
<character card and system prompt>

<<USER>>
<prompt>

<<AIBOT>>
<leave a newline blank for model to respond>

This model is not intended for supplying factual information or advice in any form

This model is merged and can be reproduced using the tools mentioned above. Please refer to all provided links for extra model-specific details.