metadata
language:
- en
tags:
- merge
license: other
library_name: transformers
pipeline_tag: text-generation
CodeRosa-70B-AB1
I wanted model that will be everyday very nice assistant with some codding abilities.
Idea was that Llama to be so censored means it must have deeper psychological understanding of human emotions. I think this part of Llama got included in this merge.
Model aqured very task centric aproach from CodeLlama Python so it must be prompted precisely. can write longer texts as well as shorter responses. I does not pose a tendency to make happy endings and insteed it can suprise and leave open scene for futher prompring.