--- language: - en pipeline_tag: text-generation tags: - quantized - 2-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - text2text-generation - mistral - roleplay - merge base_model: DZgas/GIGABATEMAN-7B model_name: GIGABATEMAN-7B model_creator: DZgas quantized_by: DZgas --- <img src="logo.png"> This is a GGUF variant of <a href=https://huggingface.co/DZgas/GIGABATEMAN-7B?not-for-all-audiences=true>GIGABATEMAN-7B</a> model. Use with <a href=https://github.com/LostRuins/koboldcpp/releases>koboldcpp</a> (do not use GPT4ALL) The most UNcensored model that I know.