zarablend-1.1-l2-7b/README.md

license, tags

license	tags
other	llama2

Model Card: Zarablend 1.1 L2 7b

This model uses Nous Hermes Llama2 7b (66%) as a base with Airoboros L2 7B GPT4 2.0 (34%) and the result of this merge was merged with LimaRP LLama2 7B Lora version of the day 07/23/2023.

This merge of models(hermes 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 Nous Hermes, 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>

Bias, Risks, and Limitations

This model 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.