--- 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. Will rather spell numbers then write them. This model is for personal use, mede for myself as experiment. I would like to make next iteration of this model in future. Mission is the same. Very nice, been able to talk about variety topics in a very emetional way with some kick for programming and with ability to teach some things. Beside all this to be good text summarizer ideally with Polish language as available option. Thase are the gols. Do I succed with this merge? I have to experiment more with that below two models more. A like this result, this was iteration worth publishing even thought it is not much tested! ### Ingridients - [Midnight-Rose-70B-v2.0.3](https://huggingface.co./sophosympatheia/Midnight-Rose-70B-v2.0.3) - [CodeLlama-70b-Python-hf](https://huggingface.co./codellama/CodeLlama-70b-Python-hf)